JP2019067365A - IMAGE PROCESSING APPARATUS, IMAGE PROCESSING SYSTEM, IMAGE PROCESSING METHOD, AND PROGRAM - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the practicality of a correctness determination. An image processing apparatus 3 generates a first histogram which is a histogram of pixel values of a first image and a second histogram which is a histogram of pixel values of a second image, and the first histogram. And the first leveling, which is the first leveled histogram, is performed by performing a leveling process in which the frequency value in the second histogram is dispersed in one or more bins located in the vicinity of the bin corresponding to the frequency value. Generates comparative information showing the comparison result between the histogram and the second leveled histogram, which is the leveled second histogram. [Selection diagram] Fig. 3

Description

  The present invention relates to an image processing apparatus, an image processing system, an image processing method, and a program.

  There is a monitoring system that performs abnormality detection and the like by analyzing an image captured by an imaging device such as a video camera. In such a system, a method is used in which a reference image serving as a determination reference is compared with a detected image obtained by imaging a sample to be determined. For example, there is known a method of performing a positive or negative determination based on a comparison result of a histogram of pixel values of a reference image and a histogram of pixel values of a detection image.

  For example, in an automatic inspection apparatus that selects a foreign object candidate by comparing an inspection image and a threshold, each pixel of the inspection image for the purpose of achieving good foreign object detection even when using an imaging device having a pixel defect. Are expanded for each luminance to expand the gradation width of the created histogram, and the image size of the expanded inspection image is reduced to generate a reduced image, and a specified image is located at a position corresponding to the pixel of the reduced image in the inspection image There is disclosed a method of setting the average value of the luminances of a pixel and a plurality of pixels adjacent to a specific pixel to the luminance of each pixel in a reduced image (Japanese Patent Application Laid-Open No. 2008-101501).

  When making a determination of correctness based on the comparison result of the histogram of the reference image and the histogram of the detected image, the detected image that should be judged as normal (matched) is abnormal due to a slight deviation of the bin to which the frequency value is voted (Mismatch) may be determined. For example, in the case of comparison using a histogram having 256 bins corresponding to 256 color components, votes in the histogram of the reference image are concentrated in the 200th bin, and votes in the histogram of the detected image are Consider the case of concentrating on 201 bins. In such a case, since the difference in hue between two adjacent bins is small, it can be determined that the hues of the reference image and the detection image substantially match. Such slight deviation of the bin may occur depending on factors other than the sample, such as a change in ambient light, an arrangement of the sample in the detection area, and the like. According to the prior art, it is not possible to sufficiently avoid such an unfair judgment as to correctness or falseness due to factors other than the sample, and it is not possible to flexibly perform the correctness judgment. Therefore, there is room for improvement in terms of the practicability of the correctness determination.

  The present invention has been made in view of the above, and it is an object of the present invention to improve the practicability of positive / negative determination.

  In order to solve the problems described above and to achieve the object, an image processing apparatus according to an aspect of the present invention includes a first histogram that is a histogram of pixel values of a first image, and a pixel value of a second image. A histogram generation unit that generates a second histogram that is a histogram of the first and second histograms, and a frequency value in the first histogram and the second histogram to one or more bins located in the vicinity of a bin corresponding to the frequency value A leveling unit for performing leveling processing for dispersing, a first leveling histogram that is the first leveled histogram, and a second leveling histogram that is the second leveled histogram. And a comparison unit that generates comparison information indicating a comparison result.

  According to the present invention, it is possible to improve the practicability of the correctness determination.

FIG. 1 is a diagram showing an example of the hardware configuration of the image processing system according to the first embodiment. FIG. 2 is a diagram illustrating an example of the hardware configuration of the information processing apparatus according to the first embodiment. FIG. 3 is a block diagram showing an example of the functional configuration of the information processing apparatus according to the first embodiment. FIG. 4 is a flowchart showing an example of processing performed by the information processing apparatus according to the first embodiment. FIG. 5 is a view showing an example of a state at the time of area setting of the setting screen according to the first embodiment. FIG. 6 is a diagram illustrating an example of a state at the time of setting a reference image of the setting screen according to the first embodiment. FIG. 7 is a diagram illustrating an example of a state at the time of setting a detection image of the setting screen according to the first embodiment. FIG. 8 is a flowchart showing a specific processing example by the histogram generation unit and the leveling unit according to the first embodiment. FIG. 9 is a diagram showing an example of a histogram before leveling according to the first embodiment. FIG. 10 is a diagram showing an example of the histogram after leveling according to the first embodiment. FIG. 11 is a diagram illustrating an example of a first state at the time of setting the threshold of the setting screen according to the first embodiment. FIG. 12 is a diagram illustrating an example of a second state at the time of setting the threshold of the setting screen according to the first embodiment. FIG. 13 is a diagram illustrating an example of the result of the correctness determination according to the first embodiment. FIG. 14 is a diagram illustrating an example of a third state at the time of setting the threshold of the setting screen according to the first embodiment. FIG. 15 is a diagram showing an example of a state when setting of the setting screen in the first embodiment is completed. FIG. 16 is a diagram illustrating an example of a first state at the time of setting the threshold of the setting screen according to the second embodiment. FIG. 17 is a diagram illustrating an example of a second state at the time of setting the threshold of the setting screen according to the second embodiment. FIG. 18 is a block diagram showing an example of a functional configuration of the information processing apparatus according to the third embodiment. FIG. 19 is a flowchart illustrating an example of processing performed by the information processing apparatus according to the third embodiment. FIG. 20 is a flowchart showing a specific processing example by the recalculation unit according to the third embodiment. FIG. 21 is a diagram showing an example of the lower limit value of the S component according to the third embodiment. FIG. 22 is a diagram showing an example of the lower limit value and the upper limit value of the V component according to the third embodiment. FIG. 23 is a diagram showing an example of the state in which the pixel is invalidated in the third embodiment. FIG. 24 is a diagram showing an example of a state at the time of setting a reference image of the setting screen according to the third embodiment. FIG. 25 is a diagram illustrating an example of a state at the time of determination processing of the setting screen according to the third embodiment. FIG. 26 is a flowchart illustrating a specific processing example of the origin moving unit according to the third embodiment. FIG. 27 is a diagram illustrating an example of a histogram before the origin movement process according to the third embodiment is performed. FIG. 28 is a diagram illustrating an example of a histogram after the origin movement process according to the third embodiment is performed. FIG. 29 is a block diagram showing an example of a functional configuration of the information processing apparatus according to the fourth embodiment. FIG. 30 is a flowchart illustrating an example of processing performed by the information processing apparatus according to the fourth embodiment. FIG. 31 is a flowchart showing a specific processing example by the color setting unit according to the fourth embodiment. FIG. 32 is a diagram showing an example of a state at the time of color setting processing of a setting screen according to the fourth embodiment. FIG. 33 is a diagram showing an example of a state at the time of setting color reflection of the setting screen according to the fourth embodiment. FIG. 34 is a view showing an example of a setting screen according to the fifth embodiment. FIG. 35 is a diagram showing an example of a state in which one designated point is designated on the setting screen according to the fifth embodiment. FIG. 36 is a diagram showing an example of a state in which two designated points are designated on the setting screen according to the fifth embodiment. FIG. 37 is a diagram showing an example of a state in which three designated points are designated on the setting screen according to the fifth embodiment. FIG. 38 is a diagram showing an example of a state in which four designated points are designated on the setting screen according to the fifth embodiment. FIG. 39 is a diagram showing an example of a state when a designated point is deleted on the setting screen according to the fifth embodiment. FIG. 40 is a diagram illustrating an example of a state after the designated point is deleted on the setting screen according to the fifth embodiment. FIG. 41 is a diagram illustrating an example of a state in which the allowable error lower limit value and the allowable error upper limit value are adjusted in the setting screen according to the fifth embodiment. FIG. 42 is a flowchart illustrating an example of processing performed by the information processing apparatus according to the fifth embodiment. FIG. 43 is a block diagram illustrating an example of a functional configuration of the information processing apparatus according to the sixth embodiment. FIG. 44 is a flowchart of an example of processing performed by the information processing apparatus according to the sixth embodiment. FIG. 45 is a flowchart of a specific process example of the extension unit according to the sixth embodiment. FIG. 46 is a diagram showing an example of a histogram before expansion according to the sixth embodiment. FIG. 47 is a diagram showing an example of a histogram after expansion according to the sixth embodiment. FIG. 48 is a diagram showing an example of a state before expansion of the setting screen according to the sixth embodiment. FIG. 49 is a diagram showing an example of a state after expansion of the setting screen according to the sixth embodiment.

  Hereinafter, embodiments of an image processing apparatus, an image processing system, an image processing method, and a program according to the present invention will be described in detail with reference to the drawings. The present invention is not limited by the following embodiments, and the constituent elements in the following embodiments include those which can be easily conceived by those skilled in the art, substantially the same ones, and so-called equivalent ranges. . Various omissions, substitutions, changes, and combinations of the constituent elements can be made without departing from the scope of the following embodiments.

First Embodiment
FIG. 1 is a diagram illustrating an example of a hardware configuration of an image processing system 1 according to the first embodiment. The image processing system 1 includes imaging devices 2 a to 2 f, an information processing device 3 (image processing device), a network 4, and an external device 5.

  The imaging devices 2a to 2f capture an object by converting light (reflected) emitted from the object into an electric signal, and the moving image (for example, 10 [FPS]) composed of a plurality of frames (still image data) It is a video camera that generates video data. The imaging devices 2a to 2f, for example, photograph a production facility that produces a plurality of products, a production line, and the like, and generate video data for performing correctness determination to detect an abnormality with respect to a workpiece (sample) that is a manufactured product. . In the present embodiment, a plurality of (six in this example) imaging devices 2a to 2f are provided, but may be one.

  The information processing device 3 is a PC (Personal Computer), a work station, or the like that functions as a device that performs the correctness determination of the work based on the video data generated by the imaging devices 2a to 2f. The information processing apparatus 3 according to the present embodiment is connected with the external device 5 constituting a production facility or the like so as to be able to communicate according to, for example, the fieldbus standard.

  The network 4 is, for example, a Ethernet (registered trademark) standard network for connecting the imaging devices 2 a to 2 f and the information processing device 3. In this case, in the network 4, data communication is performed by a protocol such as Transmission Control Protocol (TCP) / Internet Protocol (IP). In this case, the imaging devices 2a to 2f and the information processing device 3 have a MAC (Media Access Control) address for communicating according to the TCP / IP protocol, and an IP address such as a private IP address is assigned. An example of a specific configuration of the network 4 is, for example, a star wiring type in which each of the imaging devices 2a to 2f and the information processing device 3 is connected by a LAN (Local Area Network) cable to a switching hub having a plurality of ports. The network 4 is not limited to one using TCP / IP. For example, the information processing device 3 has a plurality of VGA (Video Graphics Array) terminals or USB (Universal Serial Bus) ports, and a plurality of imaging devices The configuration may be such that 2a to 2f are connected to the information processing device 3 by a VGA cable or a USB cable.

  FIG. 2 is a diagram illustrating an example of a hardware configuration of the information processing device 3 according to the first embodiment. The information processing apparatus 3 includes a central processing unit (CPU) 11, a read only memory (ROM) 12, a random access memory (RAM) 13, an external storage device 14, a display 15, a network I / F 16, a keyboard 17, a mouse 18, and a DVD. (Digital Versatile Disc) A drive 19, an external device I / F 21, and a speaker 22 are included.

  The CPU 11 is a device including one or more circuits that perform arithmetic processing to control the entire operation of the information processing device 3. The ROM 12 is a non-volatile storage device storing a program for the information processing device 3. The RAM 13 is a volatile storage device used as a work area of the CPU 11.

  The external storage device 14 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) that stores various data such as video data and setting information generated by the imaging devices 2a to 2f.

  The display 15 is a display device that displays a cursor, a menu, a window, characters, an image, a screen of an application that performs correctness determination, and the like. The display 15 is, for example, a CRT (Cathode Ray Tube) display, a liquid crystal display, a plasma display, an organic EL (Electroluminescence) display, or the like. The display 15 is connected to, for example, the main body of the information processing apparatus 3 by a VGA cable, a high-definition multimedia interface (HDMI (registered trademark)) cable, an Ethernet cable, or the like. The display 15 may have a mechanism for enabling touch panel type input operation.

  The network I / F 16 is an interface for connecting to the network 4 to perform data communication. The network I / F 16 is, for example, a NIC (Network Interface Card) that enables communication by the TCP / IP protocol. Specifically, the information processing device 3 acquires video data from the imaging devices 2 a to 2 f via the network 4 and the network I / F 16.

  The keyboard 17 is an input device for inputting characters, numerals, selection of various instructions, movement of a cursor, setting of setting information, and the like. The mouse 18 is an input device for performing selection (execution) of various instructions, selection of a processing target, movement of a cursor, setting of setting information, and the like.

  The DVD drive 19 is a device that controls reading, writing, and deletion of data to the DVD 20 as an example of a removable storage medium.

  The external device I / F 21 is an interface for connecting to the external device 5 and performing data communication. The external device I / F 21 is an interface card that enables communication according to, for example, the fieldbus standard. Specifically, the information processing device 3 performs data communication with the external device 5 via the external device I / F 21.

  The speaker 22 is a device that outputs sound in accordance with the operation of the application.

  The above-described CPU 11, ROM 12, RAM 13, external storage device 14, display 15, network I / F 16, keyboard 17, mouse 18, DVD drive 19, external device I / F 21, and speaker 22 are buses such as address bus and data bus Are communicably connected to each other. The display 15 is connected to the network I / F 16 when connected by an Ethernet cable. In this case, data communication is performed by a protocol such as TCP / IP.

  Note that the hardware configuration shown in FIGS. 1 and 2 is merely an example, and the image processing system 1 and the information processing apparatus 3 should be constructed using appropriate hardware and software according to the use situation. is there.

  FIG. 3 is a block diagram showing an example of the functional configuration of the information processing apparatus 3 according to the first embodiment. The information processing apparatus 3 includes a video reception unit 101 (acquisition unit), a storage unit 102, an input unit 103, an area setting unit 104, a reference image setting unit 105 (image setting unit), a detection image setting unit 106 (image setting unit), A histogram generation unit 107, a leveling unit 108, a comparison unit 109, a determination unit 110, a threshold setting unit 111, a display control unit 112, and an external output unit 113 are included.

  The video reception unit 101 performs data communication with the imaging devices 2 a to 2 f via the network 4, and receives video data from the imaging devices 2 a to 2 f. The video receiving unit 101 causes the storage unit 102 to store the received video data.

  The storage unit 102 stores various data such as video data and setting information received by the video reception unit 101.

  The input unit 103 receives an input operation by the user regarding various processes executed by the information processing device 3.

  The area setting unit 104 performs processing for setting an arbitrary area from the video (video captured by the imaging devices 2 a to 2 f) indicated by the video data. Although the method of setting the area should not be particularly limited, for example, the user operates a pointing device such as the mouse 18 on an image displayed on the display device 115 such as the display 15 to designate an arbitrary area, etc. Can be done by

  The reference image setting unit 105 performs processing for setting a reference image (first image) as a reference of determination based on the area set by the area setting unit 104.

  Based on the area set by the area setting unit 104, the detection image setting unit 106 performs processing for setting a detection image (second image) in which the sample to be determined is captured.

  The histogram generation unit 107 generates a reference histogram (first histogram) which is a histogram of pixel values of a reference image and a detection histogram (second histogram) which is a histogram of pixel values of a detection image. The pixel values for generating the histogram are not particularly limited, but, for example, HSV (Hue, Saturation, Value), HLS (Hue), Saturation (Lightness / Luminance)) may be a value indicating the position in the color space, a value indicating the luminance in gray scale (luminance value), or the like. When the reference image and the detection image are colors, pixel values indicating positions in a color space such as HSV are used. For example, when using HSV or HLS as pixel values, bins (classes) in the histogram are set corresponding to the number (for example, 256) of H components (hue), and the number of appearances (frequency value) of each H component is The corresponding bin is voted.

  The leveling unit 108 performs a leveling process on the reference histogram and the detection histogram. The leveling process is a process of distributing the frequency value in the histogram to one or more bins located in the vicinity of the bin corresponding to the frequency value. There is no particular limitation on the method of distributing the frequency value, but for example, the frequency value of the 100th bin is distributed to the 99th and 101st bins adjacent to the 100th bin. Also, it may be distributed to bins (e.g., the 98th bin, the 102nd bin, etc.) that are not directly adjacent to the 100th bin but located in the vicinity thereof. As described above, the leveling process is performed to distribute the frequency value concentrated in a certain bin to the bins located near the relevant bin. This makes it possible to reduce the influence of a slight deviation of the bins for which frequency values are voted on the determination result.

  The comparison unit 109 compares the leveling reference histogram (first leveling histogram), which is a leveled reference histogram, with the leveling detection histogram (second leveling histogram), which is a leveled detection histogram. And generates comparison information indicating the comparison result. The method for comparing the leveling histograms is not particularly limited, and any known or novel method can be used as appropriate. The form of the comparison information is determined according to the comparison method to be employed, and may be, for example, the matching rate of both leveling histograms, the detection rate indicating the probability of occurrence of abnormality (for example, the reciprocal of the matching rate), etc. .

  The determination unit 110 performs a correctness determination process of determining whether or not the reference image and the detected image match based on the comparison result by the comparison unit 109. The correctness determination process according to the present embodiment is performed by comparing comparison information with a threshold. For example, when the comparison information is a detection rate (the larger the value is, the higher the possibility of a mismatch (abnormality)), the reference image and the detection image are one when the detection rate is larger than a certain threshold (for example, 20%). It is determined that the test is not performed (the sample is abnormal). If the comparison information is a match rate (the smaller the value, the higher the possibility of a mismatch), it is determined that the reference image and the detected image do not match if the match rate is smaller than a certain threshold (for example, 80%) Be done.

  The threshold setting unit 111 sets a threshold in the correctness determination process. The method of setting the threshold is not particularly limited, but it is preferable that the threshold can be arbitrarily changed by, for example, the user inputting a predetermined operation to the input unit 103. At this time, it is preferable that the user can set the threshold while referring to a reference image, a detection image, a histogram, comparison information (detection rate and the like) and the like displayed on the display device 115 such as the display 15. This allows the user to set the threshold appropriately. For example, the increase in detection rate (the decrease in match rate) due to a change in ambient light can be set to be negligible, or the difference in sample placement (position in the detection area, sample orientation, etc.) can be ignored. It is possible to

  The display control unit 112 performs processing for causing the display device 115 to display a video (including a still image and a moving image) necessary to realize the functions of the functional units 101 to 111. The display control unit 112 according to the present embodiment includes various setting screens (screens for setting a detection area, a reference image, a detection image, a threshold, and the like), current or past images captured by the imaging devices 2a to 2f, and a reference An image, a detection image, various histograms (reference histogram, detection histogram, leveling reference histogram, leveling detection histogram, etc.), comparison information (detection rate, match rate, etc.), determination results, etc. are displayed on the display device 115.

  The external output unit 113 outputs the information generated by the functional units 101 to 111 to the external device 5. The external output unit 113 may output, for example, the comparison information generated by the comparison unit 109 and the determination result generated by the determination unit 110 to the external device 5 constituting the production facility or the like.

  The determination unit 110 and the threshold setting unit 111 may not necessarily be included in the information processing apparatus 3, and may be realized using another information processing apparatus existing in the image processing system 1. Further, in the present example, the reference image and the detection image are set from the video (video data) captured by the imaging devices 2a to 2f by the reference image setting unit 105 and the detection image setting unit 106. The method of setting the detection image is not limited to this. The reference image and the detection image should be set by an appropriate method according to the hardware configuration of the image processing system 1, the property of the sample to be monitored, and the like.

  Each of the functional units 101 to 113 is realized by, for example, one or more integrated circuits. Each of the functional units 101 to 113 may be realized by causing a processor such as the CPU 11 to execute a program, that is, software. Each of the functional units 101 to 113 may be realized by a processor such as a dedicated IC (Integrated Circuit), that is, hardware. Each of the functional units 101 to 113 may be realized by using software and hardware in combination. When a plurality of processors are used, each processor may realize one of the functional units 101 to 113 or may realize two or more of the functional units 101 to 113.

  FIG. 4 is a flowchart showing an example of processing by the information processing device 3 according to the first embodiment. Steps S <b> 101 to S <b> 108 are setting processes performed before the correctness determination process is performed. First, the area setting unit 104 performs processing for setting a detection area (S101).

  FIG. 5 is a view showing an example of a state at the time of area setting of the setting screen 151 according to the first embodiment. On the setting screen 151 of this example, a video 152 captured by the second imaging device 2b (CAM 2) is displayed, and the video 152 is switched to the video captured by the first imaging device 2a (CAM 1). It is made to be able to. In addition, the setting screen 151 is provided with an indicator 153 for specifying the time when the image 152 was taken. When the user operates the indicator 153 to specify a desired time, an image 152 corresponding to the time is displayed. In the image 152 of this example, a detection area 155 and three specimens 161a to 161c are displayed. The detection area 155 is arbitrarily set by the user's operation, and is set, for example, by performing an operation of designating an arbitrary area on the image 152 using the mouse 18 or the like. The detection area 155 of this example is set to include the images of three specimens 161a to 161c.

  Thereafter, as shown in FIG. 4, the reference image setting unit 105 performs processing for setting a reference image (S102).

  FIG. 6 is a view showing an example of a state at the time of setting a reference image of the setting screen 151 according to the first embodiment. The setting screen 151 of this example includes a reference image display unit 171, a detection image display unit 172, a histogram display unit 173, and a threshold value operation unit 174. Images in the detection area 155 are displayed on the reference image display unit 171 of this example. The image in the detection area 155 is an image cut from the past or present image 152. When the user performs an operation of pressing the OK button 179 in the setting screen 151, the image displayed on the reference image display unit 171 is stored in the storage unit 102 as the reference image 175.

  Thereafter, as shown in FIG. 4, the detection image setting unit 106 performs processing for setting a detection image (S103).

  FIG. 7 is a diagram showing an example of a state at the time of detection image setting of the setting screen 151 according to the first embodiment. The image in the detection area 155 shown in FIG. 7 is an image cut out from the past or present image 152, as in the detection area 155 shown in FIG. The image in the detection area 155 shown in FIG. 7 is different from the image in the detection area 155 shown in FIG. That is, the time when the video 152 shown in FIG. 7 was taken is different from the time when the video 152 shown in FIG. 6 was taken. The detected image display unit 172 of this example displays an image in the detection area 155 shown in FIG. 7. When the user performs an operation of pressing the OK button 179 in the setting screen 151, the image displayed on the detected image display unit 172 is stored in the storage unit 102 as a detected image 176.

  Thereafter, as shown in FIG. 4, the histogram generation unit 107 generates, in the reference image 175, a reference histogram which is a histogram of pixel values and a detection histogram which is a histogram of pixel values of the detected image 176 (S104). The conversion unit 108 generates a leveling reference histogram obtained by leveling the reference histogram and a leveling detection histogram obtained by leveling the detection histogram (S105).

  FIG. 8 is a flowchart showing a specific processing example by the histogram generation unit 107 and the leveling unit 108 according to the first embodiment. Here, an example is shown in which the value of the H (hue) component of HSV is histogrammed.

  The histogram generation unit 107 generates a reference histogram from the value of the H component of each pixel of the reference image 175, and generates a detection histogram from the value of the H component of each pixel of the detection image 176 (S151). After that, the leveling unit 108 integrates the histogram vector H obtained by vectorizing both histograms generated by the histogram generation unit 107 with the leveling matrix S to calculate a leveling vector H '(S152). That is, the leveling vector H corresponding to the reference histogram is generated by integrating the histogram vector H corresponding to the reference histogram and the leveling matrix S, and the histogram vector H corresponding to the detection histogram and the leveling matrix S are generated. The integration generates a leveling vector H ′ corresponding to the detected histogram. The following equation (1) is an example of the histogram vector H, the following equation (2) is an example of the leveling matrix S, and the following equation (3) is an example of the leveling vector H ′.

  The examples of the above formulas (1) to (3) are examples in which the number of bins of the histogram is 5, and the sizes of the histogram vector H, the leveling vector H ′, and the leveling matrix S depend on the number of bins. Change. For example, when the number of bins is 256, the sizes of the histogram vector H and the leveling vector H ′ are 256, and the size of the leveling matrix S is 256 × 256.

  Thereafter, the leveling unit 108 generates a leveled histogram based on the leveling vector H '(S153). That is, the leveling reference histogram is generated based on the leveling vector H 'corresponding to the reference histogram, and the leveling detection histogram is generated based on the leveling vector H' corresponding to the detection histogram.

  FIG. 9 is a diagram showing an example of the histogram 181 before leveling according to the first embodiment. FIG. 10 is a diagram showing an example of the histogram 182 after leveling according to the first embodiment. The histogram 181 (reference histogram or detection histogram) before leveling corresponds to the histogram vector H of Equation (1). The histogram 182 (leveling reference histogram or leveling detection histogram) after leveling corresponds to the leveling vector H 'of equation (3).

  In the histogram 181 before leveling shown in FIG. 9, the frequency value of the first bin is 0, the frequency value of the second bin is 2, the frequency value of the third bin is 3 and the frequency value of the 4th bin is 0 It has become. In the histogram 182 after leveling shown in FIG. 10, the first bin frequency value is 2/3, the second bin frequency value is 5/3, the third bin frequency value is 5/3, and the fourth bin The frequency value of is 1. That is, by the leveling process, the frequency value 2 of the second bin and the frequency value 3 of the third bin before leveling are distributed to the first bin and the fourth bin located in the vicinity of these bins.

  Note that the method of distributing the frequency value by the leveling process is not limited to the above, and should be appropriately adjusted according to the number of bins of the histogram, the characteristics of the target pixel value, and the like. The way of distributing frequency values can be adjusted by changing the configuration of the leveling matrix S. By changing the configuration of the leveling matrix S, for example, the dispersion width of frequency values to other bins can be changed. The leveling matrix S may be stored in advance in, for example, the storage unit 102, may be set by the user, or may be automatically and dynamically generated by a program.

  Thereafter, as shown in FIG. 4, the comparison unit 109 compares the leveled histograms (leveling reference histogram and leveling detection histogram) to calculate a detection rate (S106).

  The method for comparing the leveling reference histogram and the leveling detection histogram (the method for calculating the detection rate, the matching rate, and the like) is not particularly limited, and any known or novel method can be used as appropriate. For example, arithmetic methods using correlation, chi-square, intersection, Bhattacharyya distance, etc. are known (Reference: http://opencv.jp/opencv-2svn/cpp/histograms.html). The following formulas (4) and (5) are calculation formulas by correlation, the following formula (6) is a calculation formula by chi-square, the following formula (7) is a calculation formula by intersection, and the following (8) is It is a formula by Bhattacharyya distance. In the following formula, H1 represents one histogram (for example, leveling reference histogram 201), H2 represents the other histogram (for example, leveling detection histogram 202), and N represents the number of bins.

  Thereafter, the display control unit 112 displays the reference image 175, the detection image 176, the detection rate, the correctness determination result, the histogram before and after leveling, and the like on the display device 115 (S107). The threshold setting unit 111 performs processing for setting a threshold of a detection rate serving as a reference of the determination of correctness in accordance with an operation on the input unit 103 by the user (S108). At this time, if the reference image 175 or the detection image 176 is changed, the detection rate to be displayed, the result of the correctness determination, the histogram before and after the leveling, etc. are also changed. Thus, the user can appropriately set the detection rate threshold while referring to the reference image 175, the detection image 176, the detection rate, the correctness determination result, the histogram before and after equalization, etc. displayed on the display device 115. It becomes possible. The same applies to the threshold of other comparison information such as the matching rate.

  FIG. 11 is a diagram showing an example of a first state at the time of setting a threshold of the setting screen 151 according to the first embodiment. In this example, although both the reference image 175 and the detection image 176 include the three samples 161a to 161c, the arrangement of the samples 161a to 161c included in the reference image 175 and the three samples included in the detection image 176 It differs from the arrangement of 161a to 161c.

  On the histogram display unit 173, a leveling reference histogram 201 corresponding to the reference image 175 and a leveling detection histogram 202 corresponding to the detected image 176 are displayed. The leveling histograms 201 and 202 correspond to the peaks 201a and 202a corresponding to the hue of the first sample 161a, the peaks 201b and 202b corresponding to the hue of the second sample 161b, and the hue of the third sample 161c. Peaks 201c and 202c are included. Although there is some difference between the two leveled histograms 201 and 202 for each of the peaks 201a, 201b, 201b, 202b, 201c and 202c, this is due to the arrangement of each of the samples 161a to 161c. Not by absence.

  As described above, in the present embodiment, the above-described specimens 161a to 161c are compared by comparing the leveling reference histogram 201 and the leveling detection histogram 202 instead of comparing the reference histogram and the detection histogram. It is possible to reduce the effects of differences in the placement of In addition, the influence of subtle changes in hue due to changes in ambient light can also be reduced. Thereby, it becomes possible to reduce the influence of factors other than the abnormality of the specimens 161a to 161c and to perform the correctness determination appropriately.

  In the example shown in FIG. 11, as shown in the threshold value operation unit 174, the threshold of the detection rate is set to 2% (when the detection rate is 2% or more, it is determined to be abnormal (with change)). ). The threshold can be arbitrarily changed by the user operating the threshold operation unit 174. The setting screen 151 includes a detection rate display unit 191 that indicates the result of the correctness determination. Since the detection rate in the present example is 3% and exceeds 2% of the threshold value, it is determined here that “changed”.

  FIG. 12 is a diagram showing an example of the second state at the time of setting the threshold of the setting screen 151 according to the first embodiment. In the present example, the reference image 175 includes three specimens 161a to 161c, and the detection image 176 includes two specimens 161a and 161c. That is, the detected image 176 in this example does not include the sample 161 b. Accordingly, the leveling detection histogram 202 of this example includes the peak 202a corresponding to the sample 161a and the peak 202c corresponding to the sample 161c, but does not include the peak 202b corresponding to the sample 161b. Therefore, the detection rate in the present example is a relatively high value of 40%, and the correct / incorrect determination is “changed”.

  Although the detection image 176 of the first example shown in FIG. 11 includes all three specimens 161a to 161c similarly to the reference image 175, the detection image 176 of the second example shown in FIG. Only one sample 161a, 161c is included. In such a case, it may be appropriate to determine the detected image 176 of the first example as normal (no change) and to determine the detected image 176 of the second example as abnormal (with change). Therefore, by operating the threshold value operation unit 174 and setting the threshold of the detection rate within the range of 3% to 40%, a state (all the specimens 161a like the detection image 176 of the first example shown in FIG. 11) It is determined that ~ 161c is in a normal state (no change), and a state (one or more of a plurality of specimens 161a to 161c is shown as a detected image 176 of the second example shown in FIG. 12). It is possible to determine that there is no condition as abnormal (with change).

  FIG. 13 is a diagram illustrating an example of the result of the correctness determination according to the first embodiment. By setting the detection rate threshold to 3% to 40% as described above, the determination result for the detection image 176 of the first example on the upper right is “no change”, and the second lower example on the right is The determination result of the detected image 176 is “changed”. The method of setting the threshold is not limited to the above, and should be appropriately selected according to the nature of the sample, the required determination accuracy, and the like.

  FIG. 14 is a diagram illustrating an example of a third state at the time of setting the threshold of the setting screen 151 according to the first embodiment. The setting screen 151 according to the present example includes a detection rate chart display unit 177. The detection rate chart display unit 177 displays a chart showing a change in detection rate for an image (detection image 176) in the detection area 155 set to the image 152 changing in real time. In this example, the threshold of the detection rate is set to 20%, and the time when the detection rate changing in real time becomes larger than the threshold (the time when the change is made from no change to change) and the time when the detection rate becomes smaller than the threshold (The point of change from change to no change) is shown. The user may set the detection rate threshold while referring to such a chart and the image in the detection area 155.

  FIG. 15 is a diagram showing an example of a state when setting of the setting screen 151 is completed in the first embodiment. A setting content display unit 166 is included in the setting screen 151 when setting is completed. The setting content display section 166 displays information indicating the contents of the setting performed as described above, and in this example, information such as color components of the reference image 175 and the detection image 176 and a threshold of the detection rate is displayed. . The color components in this example are "color shades". The images to be compared (the reference image 175 and the detection image 176) are color images, and the hue of each pixel constituting the color image is compared. It indicates that the correctness determination is performed.

  As the color component, in addition to the “color tone”, “gray scale”, “black and white binary” and the like may be selectable. When “gray scale” is selected, the image to be compared is a gray scale image, and the leveling reference histogram (reference histogram) and the leveling detection histogram (detection histogram) are pixel values indicating gray scale gradation. It is generated using (brightness value, density value, etc.). Thereby, even in the case of comparing gray scale images, processing can be performed in the same manner as described above.

  After the setting process (setting of the detection area 155, the reference image 175, the threshold of the detection rate, etc.) as described above is completed, the determination unit 110 starts the actual correctness determination process (S109). The setting process may be performed while the actual correctness determination process is being performed.

  According to the present embodiment, by comparing the leveling reference histogram 201 and the leveling detection histogram 202, it is possible to reduce the influence of factors other than the abnormality of the specimens 161a to 161c and to perform the correctness determination appropriately. Become. In addition, since the threshold of detection rate can be set while confirming the reference image 175, the detection image 176, the leveled histograms 201 and 202, and the correctness determination result, etc., the threshold is set so that appropriate correctness determination can be performed. It becomes possible to set. This makes it possible to improve the practicability of the correctness determination.

  Other embodiments will be described below with reference to the drawings, but portions having the same or similar effects as those of the first embodiment may be denoted by the same reference numerals and description thereof may be omitted.

Second Embodiment
The image processing system 1 (information processing apparatus 3) according to the second embodiment includes a configuration suitable for the case where a grayscale image is to be compared. FIG. 16 is a diagram showing an example of the first state at the time of setting the threshold of the setting screen 221 according to the second embodiment. FIG. 17 is a diagram showing an example of the second state at the time of setting the threshold of the setting screen 221 according to the second embodiment.

  The setting screen 221 according to the present embodiment includes a difference image display unit 225. The difference image display unit 225 displays a difference image 226 (second image) in which the reference image 175 and the detection image 176 are superimposed.

  The histogram generation unit 107 according to the present embodiment generates a reference histogram that is a histogram of the reference image 175 and a difference histogram that is a histogram of the difference image 226. At this time, the pixel value used to generate both histograms is a lightness value or the like indicating gray scale gradation. The leveling unit 108 according to the present embodiment generates a leveling reference histogram obtained by leveling the reference histogram and a leveling difference histogram obtained by leveling the difference histogram. The comparison unit 109 according to the present embodiment calculates the detection rate by comparing the leveling reference histogram and the leveling difference histogram.

  As shown in FIG. 16, the leveling reference histogram 231 and the leveling difference histogram 232 are displayed in the histogram display unit 173 according to the present embodiment. A detection rate indicating the comparison result of the leveling reference histogram 231 and the leveling difference histogram 232 is displayed in the detection rate display unit 191 according to the present embodiment.

  As described above, in the present embodiment, when the image to be compared is a grayscale image, the reference image 175 (leveling reference histogram) and the detection image 176 (leveling detection histogram) are compared. Instead, the reference image 175 (leveling reference histogram) and the difference image 226 (leveling difference histogram) are compared. As a result, even in the case of handling a grayscale image that is difficult to differentiate by hue, it is possible to accurately determine whether the image is correct or not.

Third Embodiment
FIG. 18 is a block diagram showing an example of the functional configuration of the information processing apparatus 251 according to the third embodiment. An information processing apparatus 251 according to the present embodiment includes a recalculation unit 261 (excluded unit) and an origin moving unit 262 in addition to the functional units 101 to 113 of the information processing apparatus 3 according to the first embodiment.

  The recalculation unit 261 recalculates the pixel values of the reference image 175 and the detection image 176 so as to exclude pixel values having predetermined values from the targets of the histogram. For example, when the pixel value is HSV, the value of the S component is less than or equal to a predetermined lower limit (the saturation is less than or equal to the lower limit), or the value of the V component is less than or equal to the predetermined lower limit A pixel value which is equal to or less than the value or whose V component value is equal to or more than a predetermined upper limit (brightness is equal to or more than the upper limit) is invalidated.

  The origin moving unit 262 moves each origin of the leveling reference histogram and the leveling detection histogram so that the peaks in the leveling reference histogram and the leveling detection histogram are not located within the end region set in each histogram. . The end area is an area including an area near the origin and an area near the end on the horizontal axis of the histogram. The method of setting the end region is not particularly limited, and should be appropriately selected in accordance with the use situation. For example, in a histogram of 256 bins, an area of bins 1 to 10 and an area of bins 247 to 256 may be set as end areas.

  For example, when a pixel value indicating a color space is used as a target of a histogram, if a peak is located in an end area, elements for comparison are concentrated near the origin and near the end point, and defects in correctness determination It may occur. Therefore, when the peak is located in the end area, the origin of the histogram is moved so that the peak is located near the center (for example, the 128th bin) of the histogram.

  FIG. 19 is a flowchart illustrating an example of processing performed by the information processing apparatus 251 according to the third embodiment. The difference between the flowchart according to the present embodiment shown in FIG. 19 and the flowchart according to the first embodiment shown in FIG. 4 mainly relates to the flowchart according to the present embodiment, step S201 according to the recalculation unit 261 and the origin moving unit And step S202 pertaining to 262.

  After the setting of the reference image 175 and the detection image 176 is completed in steps S101 to S103, the recalculation unit 261 removes the reference image 175 and the detection image 176 so that pixel values having predetermined values are excluded from the target of the histogram. The H component is recalculated (S201). Thereafter, a reference histogram and a detection histogram are generated using the recalculated pixel value (H component) (S104), and a leveling reference histogram and a leveling detection histogram are generated from the reference histogram and the detection histogram (S105) .

  Thereafter, the origin moving unit 262 adjusts the origin position so that the peak is not located within the end region for each of the leveling reference histogram and the leveling detection histogram generated from the pixel values recalculated as described above (S202). The comparison unit 109 compares the leveling reference histogram generated as described above with the leveling detection histogram to calculate the detection rate (S106).

  FIG. 20 is a flowchart illustrating a specific processing example of the recalculation unit 261 according to the third embodiment. When the recalculation unit 261 obtains the HSV component for each pixel of the reference image and the detection image (S251), the recalculation unit 261 determines whether there is an unprocessed (recalculation process has not been performed) pixel (S252). ).

  If there is an unprocessed pixel (S252: Yes), the recalculation unit 261 determines whether S0 ≦ S and V0 ≦ V ≦ V1 hold for the HSV component of a certain pixel (S253). S indicates the value of the S component, S0 indicates the lower limit value of the S component, V indicates the value of the V component, V0 indicates the lower limit value of the V component, and V1 indicates the upper limit value of the V component.

  If S0 ≦ S and V0 ≦ V ≦ V1 hold (S253: Yes), the recalculation unit 261 sets the pixel as a valid pixel (S254), and executes step S252 again. At this time, the recalculation unit 261 may not change the pixel value of the valid pixel. On the other hand, when S0 ≦ S and V0 ≦ V ≦ V1 do not hold (S253: No), the recalculation unit 261 sets the pixel as an invalid pixel (S255), and executes step S252 again. The above process is repeated, and when there is no unprocessed pixel (S252: No), the recalculation unit 261 reflects the invalid pixel on the image (image 152, reference image 175, detected image 176, etc.) (S256).

  FIG. 21 is a diagram showing an example of the lower limit value S0 of the S component according to the third embodiment. FIG. 22 is a diagram showing an example of the lower limit value V0 and the upper limit value V1 of the V component according to the third embodiment. In FIG. 21 and FIG. 22, a color space table 271 showing the HSV color space is illustrated. When the saturation (S) becomes lower than the lower limit value S0, the entire image becomes substantially black. Further, when the lightness (V) becomes lower than the lower limit value V0, the whole screen becomes substantially black, and when the lightness (V) becomes higher than the upper limit value V1, the whole screen becomes substantially white. Therefore, pixels in which S0 ≦ S and V0 ≦ V ≦ V1 do not hold can be invalidated.

  FIG. 23 is a diagram showing an example of the state in which the pixel is invalidated in the third embodiment. In this example, S0 = 10, V0 = 30, and V1 = 100 are set. That is, the effective range of the saturation (S) is 10 or more, and the effective range of the lightness is 30 or more and 100 or less. In the example shown in FIG. 23, among the 3 × 3 pixels, pixels having S component or V component outside the effective range are invalid. A histogram is generated using only the H component of valid pixels (pixels not marked in the right figure).

  FIG. 24 is a view showing an example of a state at the time of setting a reference image of the setting screen 281 according to the third embodiment. The setting screen 281 according to this example includes an after-image display unit 285. The after-modification image display unit 285 displays an after-modification image 286 in which the result of the invalidation processing is reflected on the reference image 175. In the post-change image 286, pixels of background portions other than the specimens 161a to 161c are invalidated and turned black. When the user performs an operation of pressing the OK button 179, the after-change image 286 displayed on the after-change image display unit 285 is stored as a reference image. In addition, although the reference | standard image was demonstrated here, the same may be said of a detection image.

  FIG. 25 is a diagram illustrating an example of a state at the time of determination processing of the setting screen 281 according to the third embodiment. The reference image 288 after the change by the invalidation process is displayed on the reference image display unit 171 of the setting screen 281 according to the present example, and the detected image 289 after the change by the invalidation process is displayed on the detection image display unit 172. It is done. The detection image 289 of this example does not include the specimens 161a to 161c. The background portions of the reference image 288 and the detected image 289 other than the specimens 161a to 161c are blackened by the invalidation process.

  FIG. 26 is a flowchart showing a specific processing example of the origin moving unit 262 according to the third embodiment. When the leveling unit 108 generates the leveled histogram h (i) (S281), the origin moving unit 262 sets i = 0 (S282). i represents a bin of a histogram, for example, i = 0-255. h (i) represents the frequency value corresponding to each bin. Thereafter, the origin moving unit 262 determines whether i ≦ 256 holds (S283).

  If i ≦ 256 holds (S 283: Yes), the origin moving unit 262 determines whether h (i−1) <h (i) and h (i) ≧ h (i + 1) holds (S 283: Yes) S284). However, h (-1) = h (255) and h (256) = h (0). If h (i-1) <h (i) and h (i) ≧ h (i + 1) are satisfied (S284: Yes), the origin moving unit 262 adds i to the candidate of the vertex position (S285). That is, in three adjacent bins, i corresponds to the peak position if the middle bin h (i) is greater than the immediately preceding bin h (i-1) and is greater than or equal to the immediately following bin h (i + 1) It is determined that it may be a bin. Thereafter, the origin moving unit 262 adds 1 to i (S286), and executes step S283 again. On the other hand, when h (i-1) <h (i) and h (i) ≧ h (i + 1) do not hold (S284: No), step S286 is executed without executing step S285.

  The above processing is repeated, and when i ≦ 256 does not hold (S283: No), the origin moving unit 262 calculates the average value of one or more i that have become candidates for vertex positions (S287), and the average value It is determined whether the vertex position indicated by is located within the end region of the histogram (S288). If the vertex position is located within the end region (S288: Yes), the origin moving unit 262 moves the origin position so that the vertex position is located at the center of the histogram (S289). For example, by moving the origin point by 128 bins in the histogram of 256 bins, the peak can be located approximately at the center of the histogram. If the vertex position is not located within the end region (S288: No), the origin moving unit 262 ends the routine without moving the origin position.

  FIG. 27 is a diagram showing an example of a histogram (a leveling reference histogram or a leveling detection histogram) before the origin movement process according to the third embodiment is performed. FIG. 28 is a diagram illustrating an example of a histogram after the origin movement process according to the third embodiment is performed. As shown in FIG. 27, when the peak 291 of the histogram is located near the origin, the elements for comparison are concentrated near the origin and near the end point. Therefore, as shown in FIG. 28, the peak 291 is positioned at the center of the histogram by moving the origin of the histogram.

  According to the present embodiment, it is possible to invalidate pixels that do not contribute to the correctness determination of the specimens 161a to 161c. As a result, it is possible to reduce the calculation load and the like without impairing the accuracy of the correctness determination. In addition, since it is possible to prevent concentration of the elements for comparison at the end of the histogram, it is possible to improve the accuracy of the positive / negative determination.

Fourth Embodiment
FIG. 29 is a block diagram showing an example of a functional configuration of the information processing apparatus 301 according to the fourth embodiment. An information processing apparatus 301 according to the present embodiment includes a color setting unit 311 in addition to the functional units 101 to 113, 261 and 262 of the information processing apparatus 251 according to the third embodiment shown in FIG.

  The color setting unit 311 sets a target color to be compared. The comparison unit 109 compares the leveling reference histogram and the leveling detection histogram generated for the set target color. Therefore, the correctness determination is performed only for the set target color. The method of setting the target color is not particularly limited. For example, the user may specify an arbitrary color on the image 152 displayed on the display device 115 such as the display 15 using the mouse 18 or the like. It may be

  FIG. 30 is a flowchart illustrating an example of processing performed by the information processing device 301 according to the fourth embodiment. The difference between the flowchart according to the present embodiment shown in FIG. 30 and the flowchart according to the third embodiment shown in FIG. 19 is that the flowchart according to the present embodiment mainly includes step S301 according to the color setting unit 311. It is on the point.

  After the setting of the reference image 175 and the detection image 176 is completed in steps S101 to S103, the color setting unit 311 performs a process for setting the target color (S301). The method of setting the target color is not particularly limited, but is performed by specifying an arbitrary color from the video (video 152, reference image 175, detection image 176, etc.) displayed on the setting screen. After that, the process after step S201 is performed.

  FIG. 31 is a flowchart showing a specific processing example of the color setting unit 311 according to the fourth embodiment. The color setting unit 311 first obtains the HSV components of the reference image 175 and the detection image 176 (S 351), and sets the reference hue component h 1, the reference saturation component s 1, and the reference lightness component v 1 based on the set colors. (S352). The reference hue component h1, the reference saturation component s1, and the reference lightness component v1 correspond to the H component, the S component, and the V component of the target color, respectively. Thereafter, the color setting unit 311 determines whether there is an unprocessed pixel (S353).

  When there is an unprocessed pixel (S353: Yes), the color setting unit 311 holds h1-a ≦ H ≦ h1 + b, s1-c ≦ S ≦ s1 + d, and v1-e ≦ V ≦ v1 + f for a certain pixel It is determined whether or not (S354). a to f are constants. That is, the value (H) of the H component, the value (S) of the S component, and the value (V) of the V component of the target pixel are the reference hue component h1, the reference saturation component s1, and the reference brightness component, respectively. It is determined whether it is within the error range of v1.

  If h1-a ≦ H ≦ h1 + b, s1-c ≦ S ≦ s1 + d, and v1-e ≦ V ≦ v1 + f hold (S354: Yes), the color setting unit 311 sets the pixel as a valid pixel ( S355), execute step S353 again. On the other hand, when h1-a ≦ H ≦ h1 + b, s1-c ≦ S ≦ s1 + d, and v1-e ≦ V ≦ v1 + f do not hold (S354: No), the color setting unit 311 sets the pixel as an invalid pixel. The setting is made (S356), and step S353 is executed again. If the above process is repeated and there are no unprocessed pixels (S353: No), the color setting unit 311 reflects invalid pixels on the image (image 152, reference image 175, detected image 176, etc.) (S357).

  FIG. 32 is a diagram showing an example of a state at the time of color setting processing of the setting screen 321 according to the fourth embodiment. In this example, an example in which a color is directly specified from the image 152 displayed on the setting screen 321 is shown. In this example, the user can specify a desired color by means of the pointer 325 operated by the mouse 18 or the like. A setting color display unit 327 is included in the setting screen 321 of this example. The color of the pixel designated by the pointer 325 is displayed on the setting color display unit 327. When the user performs an operation to press the OK button 179, the color displayed on the setting color display unit 327 is stored in the storage unit 102 as a target color.

  FIG. 33 is a view showing an example of a state at the time of target color reflection of the setting screen 321 according to the fourth embodiment. In this example, in the image 152 displayed on the setting screen 321, pixels having colors other than the color set as described above are invalidated. As described above, the reference image and the detection image may be set from the image 152 in which the target color is reflected, or the color specification may be performed from the reference image and the detection image.

  According to the present embodiment, it is possible to narrow down the pixels that are targets for generating a histogram or an image to only pixels having a hue desired by the user. This makes it possible to reduce the processing load and the like.

Fifth Embodiment
Although in the fourth embodiment, the color setting unit 311 sets the target color based on one color designated on the image 152 by the user, the color setting unit 311 according to the present embodiment is not limited to this. The color range of the target color is set based on one or more colors designated on the predetermined video (image 152, reference image 175, detected image 176, etc.) displayed on the display device 115 by the user. In the present embodiment, the HSL value is used as a color arrangement (pixel value) indicating a color designated by the user. However, the type of color arrangement is not limited to this, and, for example, the fourth embodiment The HSV value may be used as well as the form.

  FIG. 34 is a diagram showing an example of the setting screen 331 according to the fifth embodiment. The setting screen 331 according to the present embodiment includes an image display unit 332 that displays an image 152 captured by any of the imaging devices 2a to 2f, a reference image display unit 171 that displays a reference image 175, and a color range display unit 333. Contains.

  The color range display unit 333 is a portion that displays the color range of the target color. The color range is the width of a color arrangement (pixel values: values of hue H, saturation S, and luminance L in this embodiment) recognized as a target color. The color range display unit 333 according to the present embodiment includes a minimum value display unit 341, a maximum value display unit 342, an intermediate value display unit 343, an allowable error lower limit value setting unit 344, and an allowable error upper limit value setting unit 345. . The minimum value display unit 341 is a portion that displays the minimum value of the plurality of color arrays (HSL values) corresponding to each of the plurality of designated points designated by the user on the predetermined video. The maximum value display unit 342 is a portion that displays the maximum value of the plurality of color arrays corresponding to each of the plurality of designated points designated by the user. The intermediate value display unit 343 is an intermediate (average) value of the minimum value displayed on the minimum value display unit 341 and the maximum value displayed on the maximum value display unit 342 (for example, rounding off, rounding off or rounding off the value after the decimal point It is a part that displays the value that has been advanced. Since the hue H takes an annular value at 256 gradations (0 to 255), the maximum value “18” in the example shown in FIG. 34 corresponds to 255 + 18 = “273”, and the intermediate value “221” is , (168 + 273) /2=220.5 rounding value or advancing value. The allowable error lower limit value setting unit 344 is a part for setting the lower limit value of the allowable range of the error, and is configured to allow the user to input an arbitrary value. The allowable error upper limit value setting unit 345 is a part for setting the upper limit value of the allowable range of the error, and is configured to allow the user to input an arbitrary value.

  FIG. 35 is a diagram showing an example of a state in which one designated point is designated on the setting screen 331 according to the fifth embodiment. When the user designates an arbitrary position (in this example, a part of the handle of the scissors) on the image 152 (for example, specifying the position with a mouse and clicking), the first marker M1 is drawn at the position, and the first The HSL value (254, 170, 87 in this example) of the pixel corresponding to the marker M1 of is acquired. Since only one designated point is designated at this time, the same HSL value (254, 170, 87) is set in the minimum value display unit 341, the maximum value display unit 342, and the intermediate value display unit 343, respectively. It is displayed. In the reference image display section 171, a reference image 175 composed of pixels having HSL values from the lower limit of allowable error to the upper limit of allowable error is displayed. In the example shown in FIG. 35, a reference image 175 composed of pixels having an H value of 234 to 274 (234 to 255, 0 to 19), an S value of 150 to 190, and an L value of 67 to 107 is Is displayed.

  FIG. 36 is a diagram showing an example of a state in which two designated points are designated on the setting screen 331 according to the fifth embodiment. When the user designates the second position on the image 152, the second marker M2 is drawn at the position, and the HSL value (247, 138, 103 in this example) of the pixel corresponding to the second marker M2 is acquired Be done. At this time, the minimum value display unit 341 displays smaller values (H: 247, S: 138, and L: 87 in this example) in comparison of the HSL values of the two markers M1 and M2, and the maximum value display unit In 342, larger values (in this example, H: 254, S: 170, and L: 103) are displayed, and in the intermediate value display unit 343, intermediate values (in this example) of the respective minimum values and maximum values. H: 251, S: 154, and L: 95) are displayed. In this example, the lower limit of allowable error is set to -20, the upper limit of allowable error is set to +20, and the color range of the target color is 20 for each maximum value from a value obtained by subtracting 20 from each minimum value of HSL value. It is a range up to the added value. In the state illustrated in FIG. 36, in the reference image display section 171, the H value is in the range of 227 to 274 (227 to 255, 0 to 19), the S value is in the range of 118 to 190, and the L value is in the range of 67 to 123. A reference image 175 composed of pixels is displayed.

  FIG. 37 is a diagram showing an example of a state in which three designated points are designated on the setting screen 331 according to the fifth embodiment. When the user designates the third position on the image 152, the third marker M3 is drawn at the position, and the HSL value (253, 183, 82 in this example) of the pixel corresponding to the third marker M3 is acquired Be done. At this time, the smallest value among the HSV values of all the markers M1 to M3 (H: 247, S: 138, and L: 82 in this example) is displayed on the minimum value display unit 341, and the maximum value display unit 342 The largest value (H: 254, S: 183, and L: 103 in this example) is displayed in the middle, and the middle value display unit 343 displays the middle value (in this example) of the respective minimum and maximum values. H: 251, S: 154, and L: 95) are displayed. The reference image display section 171 is a reference image 175 composed of pixels having H values of 227 to 274 (227 to 255, 0 to 19), S values of 118 to 203, and L values of 62 to 123. Is displayed.

  In the present embodiment, it is assumed that all the three markers M1 to M3 are located in the portion of the handle of the scissors, and the portion of the handle has a color recognized as red. Hereinafter, an example in the case where a position having a color different from that of red as a designated point will be described.

  FIG. 38 is a diagram showing an example of a state in which four designated points are designated on the setting screen 331 according to the fifth embodiment. Here, a case where a position recognized as blue (a part of the eraser) is designated as the fourth designated point is exemplified. When the user specifies the fourth position on the image 152, the fourth marker M4 is drawn at the position, and the HSL value (168, 105, 72 in this example) of the pixel corresponding to the fourth marker M4 is acquired Be done. At this time, the smallest value (H: 168, S: 105, and L: 72 in this example) among the HSL values of all the markers M1 to M4 is displayed on the minimum value display unit 341, and the maximum value display unit 342 The largest value (H: 254, S: 183, and L: 103 in this example) is displayed in the middle, and the middle value display unit 343 displays the middle value (in this example) of the respective minimum and maximum values. H: 211, S: 144, and L: 88) are displayed. In the reference image display section 171, a reference image 175 composed of pixels having an H value of 148 to 274 (148 to 255, 0 to 19), an S value of 85 to 203, and an L value of 52 to 123. Is displayed. In this case, the reference image 175 includes a red area 305 recognized as red, a blue area 306 recognized as blue, and other color areas 307 recognized as colors other than red and blue (for example, gray). It will be included. This is caused by the fact that the color range of the target color is greatly expanded by designating the blue whose hue is largely different from that of red.

  As described above, when a plurality of colors (for example, red and blue) having a relatively large hue difference (for example, the difference between gradation values is equal to or more than a predetermined value) are simultaneously specified, a color not intended by the user (for example, gray) May be included in the target color range. One way to deal with such problems is to remove the bad designation points.

  FIG. 39 is a diagram showing an example of a state when a designated point is deleted on the setting screen 331 according to the fifth embodiment. FIG. 40 is a diagram showing an example of a state after the designated point is deleted on the setting screen 331 according to the fifth embodiment. Here, the case of deleting the designated point corresponding to the fourth marker M4 is exemplified. As shown in FIG. 39, when the user re-specifies the position of the fourth marker M4 by clicking on the image 152 as shown in FIG. 39, the fourth marker M4 is deleted from the image 152 as shown in FIG. The display in 333 and the reference image 175 return to the state (state shown in FIG. 37) before specifying the position corresponding to the fourth marker M4. Thus, by allowing the user to delete the designated point arbitrarily, it is possible to adjust the color range of the target color appropriately and simply.

  Further, in the present embodiment, the user can adjust the allowable error lower limit value and the allowable error upper limit value to arbitrary values.

  FIG. 41 is a diagram showing an example of a state in which the allowable error lower limit value and the allowable error upper limit value are adjusted on the setting screen 331 according to the fifth embodiment. In this example, all lower limit values of the allowable error corresponding to each HSL value are changed from -20 to -4, the upper limit value of the allowable error corresponding to the H value is changed from +20 to +7, and the allowable error corresponding to the S value The upper limit value is changed from +20 to +8, and the allowable error upper limit value corresponding to the L value is changed from +20 to +8. Accordingly, the color range of the target color is H value: 243 to 261 (243 to 255, 0 to 6), S value: 134 to 191, and L value: 78 to 111, and the reference image display unit 171 A reference image 171 is displayed that includes a red area 305 'composed of pixels with the adjusted HSL value. As described above, by allowing the user to arbitrarily adjust the allowable error lower limit value and the allowable error upper limit value, it is possible to more appropriately and simply adjust the color range of the target color.

  FIG. 42 is a flowchart illustrating an example of processing by the information processing device 301 according to the fifth embodiment. Here, as described above, a process example in which the user designates a plurality of designated points on the image 152 and sets the color range of the target color based on the HSL value corresponding to each designated point will be described. The color setting unit 311 (see FIG. 29) according to the present embodiment first reads an initial value related to the process of setting the color range of the target color from the storage unit 101 (S501). The initial value includes an upper limit (for example, 10) of designated points that can be designated on the image 152 by the user. Thereafter, the color setting unit 311 receives a click operation by which the user designates an arbitrary position on the image 152 via the user interface (S502).

  The color setting unit 311 determines whether a marker is present at the position clicked by the user on the image 152 (S503). If a marker does not exist at the clicked position (S 503: No), the color setting unit 311 determines whether the number of markers (the number of clicks or the number of designated points) has reached the upper limit (S 504). If the number of markers has not reached the upper limit (S504: No), the color setting unit 311 adds a marker at the clicked position (S505), and a color array (HSL of pixels corresponding to the position of the added marker) A value) is acquired (S506), and the color range is calculated as described above based on the acquired one or more color arrays (S510). On the other hand, if the number of markers has reached the upper limit (S504: Yes), for example, if ten markers are already arranged on the image 152, a plurality of markers already existing without adding a new marker The color range is calculated based on each color array corresponding to (S510).

  If the marker is present at the clicked position (S503: Yes), the color setting unit 311 deletes the marker present at the clicked position (S507), and deletes the color array corresponding to the deleted marker (S508). ). Thereafter, the color setting unit 311 determines whether or not there is one or more markers on the image 152 (S509), and if there is not one or more markers (no one) (S509: No), the process returns to step S502. If there is one or more markers (S509: Yes), the color range is calculated based on the color array corresponding to each marker (S510).

  After that, the color setting unit 311 updates the target color image (the reference image 175 in the example shown in FIGS. 34 to 41) composed of the pixels having the color array included in the calculated color range (S511). It is determined whether there is a request for color designation from the user (S512). If there is no request (S512: No), this routine ends, and if there is a request (S512: Yes), the process returns to step S502.

  In the above, the problem (the problem that an unintended color is included in the color range of the target color) occurs when a plurality of colors (for example, red and blue) with relatively large hues are used as designated points, Although the example solved by deleting the designated point corresponding to one color (for example, blue) has been shown, the embodiment is not limited to this. For example, when one or more designated points are designated in the red part and one or more designated points are designated in the blue part, the color range may be divided into two, red and blue. Also, the color range may be divided into three or more areas.

  That is, the color range may be divided into a plurality of parts according to the characteristics of the color arrangement of a plurality of designated points. For example, when there are a plurality of designated points, the tone value difference of the pixel value (for example, H value) indicating the hue is equal to or greater than a predetermined value (for example, the H value difference of 256 tones is 50 or more) ) May be set by dividing the color range into a plurality.

  For example, three designated points having HSV values as a color array include a first designated point (65, 34, 124), a second designated point (232, 230, 200), and a third designated point (45, 64, 98) are designated, the allowable error lower limit value is −10, and the allowable error upper limit value is +10. In this case, based on the first designated point (65, 34, 124) and the third designated point (45, 64, 98), the H value range is 35 to 75, and the S value range is 24 to 74. , V value range is 88 to 134, and the H value range is 222 to 242, the S value range is based on the second designated points (232, 230, 200). A second color range can be set, where the range 220-240, V-value is 190-210. The algorithm for dividing and setting the color range is not limited to the above, and should be appropriately determined in accordance with the use conditions and the like.

  As described above, according to the present embodiment, the color range of the target color is set based on one or more colors designated by the user. This makes it possible to set the target color more easily.

Sixth Embodiment
FIG. 43 is a block diagram illustrating an example of a functional configuration of the information processing device 351 according to the sixth embodiment. The information processing apparatus 351 according to the present embodiment includes an expansion unit 361 in addition to the functional units 101 to 113, 261, 262, and 311 of the information processing apparatus 301 according to the fourth or fifth embodiment shown in FIG. ing.

  The extension unit 361 performs extension processing for extending the peaks in the leveling reference histogram and the leveling detection histogram. The comparison unit 109 includes an expanded reference histogram (first expanded histogram) which is an expanded leveling reference histogram, and an expanded detection histogram (second expanded histogram) which is an expanded leveled detection histogram. The comparison information which shows the comparison result with is generated.

  The method of the expansion process is not particularly limited, but the peak width may be expanded in the horizontal axis (bin axis) direction, or the peak height may be expanded or reduced in the vertical axis (frequency value axis) direction. Preferably, the peak shape is expanded in the horizontal axis direction so that no gap is formed in the peak.

  FIG. 44 is a flowchart illustrating an example of processing by the information processing device 351 according to the sixth embodiment. The difference between the flowchart according to the present embodiment shown in FIG. 44 and the flowchart according to the fourth embodiment shown in FIG. 30 is that the flowchart according to the present embodiment mainly includes steps S401 and S402 according to the expanding unit 361. The point is that

  After the origin position of the histogram is adjusted by the origin moving unit 262 in step S202, the expanding unit 361 expands the leveled histogram (leveling reference histogram and leveling detection histogram) (S401). Thereafter, the comparison unit 109 compares the expanded two histograms (the expanded reference histogram and the expanded detection histogram) to calculate a detection rate (S402). After that, the process after step S107 is performed.

  FIG. 45 is a flowchart illustrating a specific processing example of the expanding unit 361 according to the sixth embodiment. The expanding unit 361 obtains the leveling vector H '(generated at step S152 in FIG. 8) (S451), and generates the expanded matrix E corresponding to the peak in the histogram corresponding to the leveling vector H' (S452). Thereafter, the expansion unit 361 integrates the leveling vector H 'and the expansion matrix E to generate an expansion vector H "(S453).

  The following equation (9) is a first example of the leveling vector H ′, the following equation (10) is a first example of the expansion matrix E, and the following equation (11) is an expansion vector H ′ ′. This is a first example.

  In the example of the above equations (9) to (11), the number of bins of the histogram is 4, and the peaks in the first bin and the second bin of the leveled histogram corresponding to the leveling vector H ′ It is formed.

  The following equation (12) is a second example of the leveling vector H ′, the following equation (13) is a second example of the expansion matrix E, and the following equation (14) is an expansion vector H ′ ′. This is a second example.

  In the example of the equations (12) to (14), the number of bins of the histogram is 4, and a peak is formed in the portion of the second bin of the leveled histogram corresponding to the leveling vector H '.

  The sizes of the leveling vector H ', the expansion vector H' 'and the expansion matrix E change according to the number of bins. Further, the expansion matrix E changes in accordance with the peak position, peak width, peak height and the like of the leveling vector H '. The expansion matrix E may be set by the user or may be generated automatically and dynamically by the program.

  Thereafter, the expansion unit 361 generates an expanded histogram based on the expansion vector H ′ ′ (S454). That is, an expanded reference histogram is generated based on the expanded vector H ′ ′ corresponding to the leveling reference histogram, and an expanded detection histogram is generated based on the leveled vector H ′ ′ corresponding to the leveled detection histogram.

  FIG. 46 is a diagram showing an example of a histogram before expansion according to the fifth embodiment. FIG. 47 is a diagram showing an example of a histogram after expansion according to the fifth embodiment. The histogram before expansion shown in FIG. 46 corresponds to the leveling reference histogram or the leveling detection histogram. The expanded histogram shown in FIG. 47 corresponds to the expanded reference histogram or the expanded detection histogram.

  In FIG. 46, a broken line 370 including three peaks 371a to 371c before expansion and an expansion area 373 before expansion are illustrated. The expanded area 373 is a rectangular area set to include three peaks 371 a to 371 c. The expanded area 373 in this example is formed by a line connecting the point a (0, 0), the point b (30, 0), the point c (0, 28000), and the point d (40, 28000). The three peaks 371a to 371c in this example are concentrated in some of the bins (in this example, the bins near the origin). Such a state occurs, for example, when the ratio of the area occupied by the specimens 161a to 161c (the object having a hue) to the area of the entire detection region 155 is small. When comparison is performed using such a histogram, the accuracy of the correct / incorrect determination may decrease.

  In FIG. 47, a broken line 370 'including three peaks 371a' to 371c 'after expansion and an expansion area 373' after expansion are illustrated. The expanded area 373 ′ after expansion connects the point a ′ (0, −450), the point b ′ (250, −450), the point c ′ (0, 3400), and the point d ′ (250, 3400) It is formed by line segments. Thus, the expansion process in this example is performed without changing the total number of bins (256). Such an expansion process disperses the elements constituting the polygonal line 370 'including the three peaks 371a' to 371c 'throughout the entire histogram. By distributing the elements to be compared, it is possible to improve the accuracy of the correctness determination. Note that the size, shape, and expansion amount of the expansion areas 373 and 373 'are merely examples, and the method of setting the expansion areas 373 and 373' should be appropriately selected according to the use situation.

  FIG. 48 is a diagram showing an example of a state before expansion of the setting screen 371 according to the sixth embodiment. The reference image 175 in this example is an image showing only the background 374. The detection image 176 in this example is an image in which one sample 161 a is present on the background 374. In the detection image 176 of this example, the ratio of the area of the subject 161a to the area of the entire detection image 176 is considerably small.

  The histogram display unit 173 before expansion displays the histogram before expansion, that is, the leveling reference histogram 375 corresponding to the reference image 175 and the leveling detection histogram 376 corresponding to the detection image 176. The leveling reference histogram 375 includes a peak 380 a corresponding to the hue of the background 374. The leveling detection histogram 376 includes a peak 380 b corresponding to the hue of the background 374 and a peak 381 corresponding to the hue of the specimen 161 a. The ratio of the elements constituting the peak 381 to all the elements constituting the leveling detection histogram 376 is considerably small. Therefore, the difference between the leveling reference histogram 375 and the leveling detection histogram 376 is small, and the value of the detection rate displayed on the detection rate display unit 191 is a very low value of 4.0%.

  FIG. 49 is a diagram showing an example of a state after expansion of the setting screen 371 according to the sixth embodiment. In the histogram display unit 173 after expansion, an expanded reference histogram, that is, an expanded reference histogram 391 obtained by expanding the leveling reference histogram 375, and an expanded detection histogram 392 obtained by expanding the leveling detection histogram 376. And are displayed. The expanded reference histogram 391 includes an expanded peak 380 a ′ corresponding to the hue of the background 374. The expanded detection histogram 392 includes an expanded peak 380b 'corresponding to the hue of the background 374 and an expanded peak 381' corresponding to the hue of the specimen 161a. As shown in FIG. 49, the difference between the expanded reference histogram 391 and the expanded detection histogram 392 is quite large, and the value of the detection rate displayed in the detection rate display section 191 becomes a considerably large value of 69.0%. There is.

  As described above, by subjecting the leveled histogram to expansion processing, even if the difference between the reference image 175 and the detected image 176 is small, the histogram corresponding to the reference image 175 and the detected image 176 can be handled. It is possible to make the difference with the histogram to be large. This makes it possible to improve the sensitivity of the correctness determination. The degree of dilation may be adjustable by the user. For example, when the operation to increase the sensitivity is input to the input unit 103, the expansion unit 361 generates the expansion matrix E such that the degree of expansion is increased. Thereby, the user appropriately checks the threshold of the detection rate and the degree of expansion while confirming the reference image 175, the detection image 176, the histograms 375, 376, 391, 392, the detection rate, etc. displayed on the setting screen 371. It becomes possible to adjust. This makes it possible to further improve the practicability of the correctness determination.

  In the description of the sixth embodiment, an example in which the recalculation unit 261, the origin moving unit 262, and the color setting unit 311 are included is shown. However, the recalculation unit 261, the origin moving unit 262 , And all or part of the color setting unit 311 may not be included.

  In the first to sixth embodiments, the reference image and the detection image are set based on an arbitrary area of the video represented by the video data, but the present invention is not limited to the embodiment. For example, a still image captured by a device for capturing a still image such as a digital camera may be used as a reference image or a detected image, or the reference image is a still image captured by a device for capturing a still image. May be set based on video data, or vice versa.

  When at least a part of various functions of the image processing system 1 and the information processing devices 3, 251, 301, 351 according to the first to sixth embodiments are realized by the execution of a program, the program is incorporated in ROM etc. in advance. Provided. Also, the program may be provided as a file in an installable format or an executable format, recorded on a computer readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD, and the like. Also, the program may be stored on a computer connected to a network such as the Internet, and may be configured to be provided by being downloaded via the network. Also, the program may be configured to be provided or distributed via a network such as the Internet. Further, the program may be configured as a module including at least a part of each of the functions described above.

  While the embodiments of the present invention have been described above, the above embodiments are presented as examples, and are not intended to limit the scope of the invention. The above novel embodiments can be implemented in other various forms, and various omissions, substitutions, and modifications can be made without departing from the scope of the invention. The above-described embodiment and the modifications thereof are included in the scope and spirit of the invention, and are included in the invention described in the claims and the equivalent scope thereof.

DESCRIPTION OF SYMBOLS 1 Image processing system 2a-2f Imaging device 3, 251, 301, 351 Information processing apparatus 4 Network 5 External device 11 CPU
12 ROM
13 RAM
14 External Storage 15 Display 16 Network I / F
17 Keyboard 18 Mouse 19 DVD Drive 20 DVD
21 External Device I / F
Reference Signs List 22 speaker 101 image receiving unit 102 storage unit 103 input unit 104 area setting unit 105 reference image setting unit 106 detection image setting unit 107 histogram generation unit 108 equalization unit 109 comparison unit 110 determination unit 111 threshold setting unit 112 display control unit 113 external Output unit 115 Display device 151, 221, 281, 321, 331, 371 Setting screen 152 Image 153 Indicator 155 Detection area 161a to 161c Sample 166 Setting content display unit 171 Reference image display unit 172 Detection image display unit 173 Histogram display unit 174 Threshold Operation unit 175, 288 Reference image 176, 289 Detection image 177 Detection rate chart display section 179 OK button 181 Histogram before equalization 182 Histogram after equalization 191 Detection rate display unit 201, 231 Leveling reference histogram 202 leveling detection histogram 201a, 201b, 201c, 202a, 202b, 202c, 291, 371a to 371c, 371a 'to 371c', 380a, 380a ', 380b, 380b', 381, 381 'peak 225 difference Image display unit 226 Difference image 232 Leveling difference histogram 261 Recalculation unit 262 Origin moving unit 271 Color space table 285 Modified image display unit 286 Modified image 305, 305 'Red region 306 Blue region 307 Other color region 311 Color setting unit 325 pointer 327 set color display unit 332 image display unit 333 color range display unit 341 minimum value display unit 342 maximum value display unit 343 intermediate value display unit 344 tolerance lower limit value setting unit 345 tolerance upper limit value setting unit 361 expansion unit 370 , 3 0 'polygonal line 373, 373' extension region 374 background 391 Scaling reference histogram 392 Scaling detection histogram M1~M4 marker

JP, 2006-194869, A

Claims (19)

A histogram generation unit that generates a first histogram that is a histogram of pixel values of the first image and a second histogram that is a histogram of pixel values of the second image;
A leveling unit that performs a leveling process of distributing the frequency values in the first histogram and the second histogram into one or more bins located near the bins corresponding to the frequency value;
A comparison unit that generates comparison information indicating a comparison result of a first leveling histogram that is the first histogram that has been leveled and a second leveling histogram that is the second histogram that is leveled. ,
An image processing apparatus comprising: A determination unit that performs a determination process of determining whether the first image and the second image match, based on the comparison information and a threshold value;
A threshold setting unit configured to set the threshold;
The image processing apparatus according to claim 1, further comprising: An exclusion unit for excluding the pixel value having a predetermined value from the target of the histogram,
The image processing apparatus according to claim 1, further comprising: The pixel value includes an HSV component,
The target value of the histogram is the value of the H component,
The exclusion unit is a value of the H component in which the value of the S component is less than or equal to a predetermined lower limit, the value of the V component is less than or equal to a predetermined lower limit, or the value of the V component is greater than or equal to a predetermined upper limit Exclude from
The image processing apparatus according to claim 3. The origins of the first leveling histogram and the second leveling histogram are moved so that peaks in the first leveling histogram and the second leveling histogram are not located within a predetermined end region. Origin mover,
The image processing apparatus according to any one of claims 1 to 4, further comprising: Color setting unit to set target color,
And further
The comparison unit compares the first leveling histogram generated using the pixel value corresponding to the target color with the second leveling histogram.
The image processing apparatus according to any one of claims 1 to 5. The color setting unit sets the target color based on a color designated by a user on a predetermined image displayed on a display device.
The image processing apparatus according to claim 6. The color setting unit sets a color range of the target color based on one or more colors designated by the user.
The image processing apparatus according to claim 7. The color setting unit divides and sets the color range into two or more when a plurality of colors having gradation value differences of pixel values equal to or greater than a predetermined value are designated.
The image processing apparatus according to claim 8. The leveling unit generates a vector of the first leveling histogram by integrating a vector of the first histogram and a leveling matrix for performing the leveling process, and the second level histogram Generating a vector of the second leveling histogram by integrating a vector with the leveling matrix,
The image processing apparatus according to any one of claims 1 to 9. An expanding unit that performs an expanding process to expand peaks in the first leveling histogram and the second leveling histogram;
And further
The comparison unit compares the result of comparison between a first expanded histogram, which is the expanded first equalization histogram, and a second expanded histogram, which is the expanded second equalization histogram. Generating the comparison information to indicate
The image processing apparatus according to any one of claims 1 to 10. The expansion unit generates a vector of a first expanded histogram by integrating the vector of the first equalization histogram and the expansion matrix for performing the expansion process, and the second equalization standard is generated. Generating a vector of the second expanded histogram by integrating the vector of the generalized histogram with the expanded matrix;
The image processing apparatus according to claim 11. The expansion matrix is generated dynamically according to the position of the peak,
An image processing apparatus according to claim 12. If the image to be compared is grayscale,
The first image is a reference image to be a reference of comparison,
The second image is a difference image obtained by superposing the reference image and a detection image to be compared.
The image processing apparatus according to any one of claims 1 to 13. An acquisition unit for acquiring video data;
An image setting unit configured to set at least one of the first image and the second image based on the video data;
The image processing apparatus according to any one of claims 1 to 14, further comprising: An image processing apparatus according to claim 15;
An imaging device for generating the video data;
Equipped with
The acquisition unit acquires the video data from the imaging device.
Image processing system. Including a plurality of said imaging devices,
The image setting unit sets the first image or the second image from among current or past videos captured by a plurality of the imaging devices.
The image processing system according to claim 16. Generating a first histogram, which is a histogram of pixel values of the first image, and a second histogram, which is a histogram of pixel values of the second image;
Performing a leveling process of dispersing the frequency values in the first histogram and the second histogram into one or more bins located near the bins corresponding to the frequency values;
Generating comparison information indicating a comparison result between a first leveling histogram, which is the first histogram that has been leveled, and a second leveling histogram, which is the second histogram that is leveled;
Image processing method including: On the computer
Processing to generate a first histogram that is a histogram of pixel values of the first image and a second histogram that is a histogram of pixel values of the second image;
Leveling processing for dispersing frequency values in the first histogram and the second histogram into one or more bins located near bins corresponding to the frequency values;
A process of generating comparison information indicating a comparison result of a first leveling histogram, which is the first histogram that has been leveled, and a second leveling histogram, which is the second histogram that is leveled;
A program that runs

Images