JP2008140208A - Image processing device, pattern extraction method, and pattern extraction program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve processing speed and accuracy of pattern matching. <P>SOLUTION: An MFP 100 comprises an image reading section for acquiring image data, a resolution conversion section 301 for creating a first reduced image data and a second reduced image data made of a plurality of pixels in which positions of the image data are different from the plurality of pixels included in the first reduced image data so that the first number of pixels is thinned out from the image data in the X-axis direction and the second number of pixels is thinned out from the image data in the Y-axis direction; a first binarizing section 303A and second binarizing section 303B which binarize the first and second reduced image data and respectively create first and second binary data; and a first certification section 305A, a second certification section 305B, and a determination section 307 for determining whether or not either of first binary image and second binary image includes a designated pattern. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, a pattern extraction method, and a pattern extraction program, and more particularly to an image processing apparatus, a pattern extraction method, and a pattern extraction program that extract a predetermined pattern from image data.

  In recent years, development of a pattern matching technique for reading a document with a scanner or the like and determining whether or not the obtained image data includes a predetermined pattern has been developed. Usually, in order to process pattern matching at high speed, reduced image data with reduced resolution of image data is used. However, by reducing the resolution, information that was present in the original image data is lost, so the pattern is included in the original image data, but part of the pattern is not present in the reduced image data, There is a problem that the pattern may not be extracted. Techniques for coping with this problem are described in Japanese Patent Application Laid-Open No. 2001-31725 (Patent Document 1) and Japanese Patent Application Laid-Open No. 2001-31726 (Patent Document 2).

Further, binary data obtained by binarizing image data or reduced image data is used to process pattern matching at high speed. However, by binarizing, the original image data or reduced image data exists. Since the original information is lost, the original image data includes a pattern, but the binarized data does not have a part of the pattern, and the pattern may not be extracted. There is.
JP 2001-31725 A JP 2001-31726 A

  The present invention has been made to solve the above-described problems, and one of the objects of the present invention is to provide an image processing apparatus that improves the processing speed of pattern matching and improves accuracy.

  Another object of the present invention is to provide a pattern extraction method that improves pattern matching processing speed and accuracy.

  Still another object of the present invention is to provide a pattern extraction program that improves the processing speed of pattern matching and improves accuracy.

  In order to achieve the above-described object, according to one aspect of the present invention, an image processing device outputs image data defining positions and pixel values of a plurality of pixels arranged in a first direction and a second direction. Image data acquisition means for acquiring and reduction of a plurality of pixels by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the acquired image data The reduced image generating means for generating an image and the reduced image generating means include a first reduced image and a second pixel composed of a plurality of pixels whose positions in the image data are different from the plurality of pixels included in the first reduced image. A binarization unit that generates the first and second binarized images by binarizing the generated first and second reduced images, and the first binarization Either the image or the second binarized image has a predetermined pattern Comprising a pattern matching unit that determines whether including down, the.

  According to this aspect, a binary image obtained by binarizing the generated reduced image by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the image data. Since it is determined whether or not the digitized image includes a pattern, it is possible to improve the processing speed by reducing the number of pixels and the data amount to be subjected to pattern matching. Further, when image data including a predetermined pattern is reduced and binarized, the binarized image may or may not include a pattern, but the first reduced image and the second reduced image respectively. Since the pixels included in are different in position in the image data, one of them includes a pattern. For this reason, since it is determined whether one of the first binarized image and the second binarized image includes a predetermined pattern, the accuracy of pattern matching is improved. As a result, it is possible to provide an image processing apparatus that improves the processing speed of pattern matching and improves accuracy.

  Preferably, the reduced image generating unit is configured to reduce the first image in the first direction from the position in the image data of the plurality of pixels included in the first reduced image to the first number and the first number. A second reduced image composed of a plurality of pixels that are one or more and two or less in the direction of 2 is generated.

  Preferably, the binarization unit includes a peripheral pixel density detection unit that detects the density of pixels around the processing target pixel, and a white pixel in which the detected peripheral pixel density is equal to or lower than a predetermined density. A first binarization unit that binarizes using one threshold value; and a second binarization unit that binarizes using a second threshold value when no white pixel exists. .

  Preferably, the density detection unit detects the density of the pixels arranged in the first direction with respect to the processing target pixel.

  According to another aspect of the present invention, a pattern extraction method receives a step of receiving image data defining positions and pixel values of a plurality of pixels arranged in a first direction and a second direction. Generating a first reduced image composed of a plurality of pixels by thinning out a first number of pixels in a first direction and thinning out a second number of pixels in a second direction from the image data; The plurality of pixels included in the first reduced image is image data by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the obtained image data. Generating a second reduced image composed of a plurality of pixels having different positions in the image, and generating first and second binarized images obtained by binarizing the generated first and second reduced images, respectively. Step and first binarization At least one image and the second binarized image includes the steps of: determining whether including a predetermined pattern.

  According to this aspect, it is possible to provide a pattern extraction method that improves the processing speed and improves the accuracy of pattern matching.

  According to still another aspect of the present invention, a pattern extraction program receives and accepts image data defining positions and pixel values of a plurality of pixels arranged in a first direction and a second direction. Generating a first reduced image consisting of a plurality of pixels by thinning out a first number of pixels in a first direction and thinning out a second number of pixels in a second direction from the obtained image data; The plurality of pixels included in the first reduced image is an image obtained by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the received image data. Generating a second reduced image including a plurality of pixels having different positions in the data, and generating first and second binarized images obtained by binarizing the generated first and second reduced images, respectively. And steps to At least one of the first binarized image and the second binarized image is executed a step of determining whether containing a predetermined pattern, to the computer.

  According to this aspect, it is possible to provide a pattern extraction program that improves the processing speed and improves the accuracy of pattern matching.

  Embodiments of the present invention will be described below with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.

  FIG. 1 is a diagram showing an overall outline of an image forming system according to one embodiment of the present invention. Referring to FIG. 1, an image forming system 1 includes an MFP (Multi Function Peripheral) 100 as an image forming apparatus connected to a network 2 and computers 3, 3A, 3B, and 3C, respectively. Digital camera 4, digital video camera 5, and portable information terminal 6.

  MFP 100 includes a scanner for reading a document, an image forming unit for forming an image on a recording medium such as paper based on image data, and a facsimile, and includes an image reading function, a copying function, and a facsimile transmission / reception function.

  Computers 3, 3 </ b> A, 3 </ b> B, and 3 </ b> C are general personal computers, and a printer driver program for controlling MFP 100 is installed. Computers 3, 3 </ b> A, 3 </ b> B, and 3 </ b> C output print data or image data generated when they execute an application program to MFP 100. MFP 100 performs image processing on print data or image data input from portable information terminal 6, or forms an image on a recording medium based on the print data or image data. Furthermore, the computers 3, 3A, 3B, 3C also function as image processing apparatuses.

  The digital camera 4 and the digital video camera 5 store captured still images or moving images, and output image data of the still images or moving images to the MFP 100 to which they are connected. The MFP 100 performs image processing on the input still image data, and forms a still image on a recording medium such as paper based on the still image data. When image data of a moving image is input, image data of one frame image is processed, and an image is formed on a recording medium based on the image data of one frame image. As with the computers 3, 3 A, 3 B, 3 C, the portable information terminal 6 outputs data or image data generated by executing an application program to the MFP 100. MFP 100 performs image processing on data or image data input from portable information terminal 6 and forms an image on a recording medium based on the image data.

  The network 2 is a local area network (LAN), and the connection form may be wired or wireless. The network 2 is not limited to a LAN, and may be a wide area network (WAN), the Internet, or the like.

  FIG. 2 is a perspective view showing the appearance of the MFP. Referring to FIG. 2, MFP 100 includes an automatic document feeder (ADF) 10, an image reading unit 20, an image forming unit 40, and a paper feeding unit 50. The ADF 10 handles a plurality of documents mounted on the document table, and sequentially conveys them to the image reading unit 20 one by one. The image reading unit 20 optically reads image information such as photographs, characters, pictures, and the like from a document and acquires image data. When the image data is input, the image forming unit 40 forms an image on a sheet based on the image data. The image forming unit 40 forms an image using toners of four colors, cyan, magenta, yellow, and black. The paper feed unit 50 stores paper and supplies the stored paper to the image forming unit 40 one by one. MFP 100 includes an operation panel 9 on the upper surface thereof.

  FIG. 3 is a block diagram illustrating an example of a hardware configuration of the MFP. Referring to FIG. 3, MFP 100 includes main circuit 101, facsimile unit 60, communication control unit 61, ADF 10, image reading unit 20, image processing unit 30, image forming unit 40, and paper feeding unit. 50. The main circuit 101 includes a central processing unit (CPU) 111, a RAM (Random Access Memory) 112 used as a work area of the CPU 111, a ROM (Read Only Memory) 113 for storing programs executed by the CPU 111, and the like. A display unit 114, an operation unit 115, a hard disk drive (HDD) 116 as a mass storage device, and a data communication control unit 117. The CPU 111 is connected to the display unit 114, the operation unit 115, the HDD 116, and the data communication control unit 117, and controls the entire main circuit 101. The CPU 111 is connected to the facsimile unit 60, the communication control unit 61, the ADF 10, the image reading unit 20, the image processing unit 30, the image forming unit 40, and the paper feeding unit 50, and controls the entire MFP 100.

  The display unit 114 is a display device such as a liquid crystal display (LCD) or an organic ELD (Electro Luminescence Display), and displays an instruction menu for the user, information about acquired image data, and the like. The operation unit 115 includes a plurality of keys, and accepts input of various instructions, data such as characters and numbers by user operations corresponding to the keys. The operation unit 115 includes a touch panel provided on the display unit 114. The display unit 114 and the operation unit 115 constitute the operation panel 9.

  The data communication control unit 117 includes a LAN terminal 118 that is an interface for communicating with a communication protocol such as TCP (Transmission Control Protocol) or FTP (File Transfer Protocol), and a serial communication interface terminal 119. The data communication control unit 117 transmits / receives data to / from an external device connected to the LAN terminal 118 or the serial communication interface terminal 119 in accordance with an instruction from the CPU 111.

  When a LAN cable for connecting to the network 2 is connected to the LAN terminal 118, the data communication control unit 117 is connected to another MFP, scanner, printer, or computer 3, 3A, which is connected via the LAN terminal 118. Communicate with 3B, 3C. When a device is connected to the serial communication interface terminal 119, the data communication control unit 117 communicates with a device connected to the serial communication interface terminal 119, for example, the digital camera 4, the digital video camera 5, or the portable information terminal 6. Communicate and input / output image data. The serial communication interface terminal 119 can be connected to a memory card 119A incorporating a flash memory. The CPU 111 controls the data communication control unit 117 to read a program to be executed by the CPU 111 or the image processing unit 30 from the memory card 119A, and stores the read program in the RAM 112 and executes it.

  A recording medium for storing a program to be executed by the CPU 111 or the image processing unit 30 is not limited to the memory card 119A, but a flexible disk, a cassette tape, an optical disk (CD-ROM (Compact Disc-Read Only Memory) / MO). (Magnetic Optical Disc / MD (Mini Disc) / DVD (Digital Versatile Disc)), IC card (including memory card), optical card, mask ROM, EPROM (Erasable Programmable ROM), EEPROM (Electrical ROM, etc.) Further, the CPU 111 may be programmed from a computer connected to the Internet. The program is downloaded and stored in the HDD 116, or the computer connected to the Internet writes the image data storage program in the HDD 116, and the program stored in the HDD 116 is loaded into the RAM 112 and the CPU 111 or the image processing unit 30. The program here includes not only a program that can be directly executed by the CPU 111 or the image processing unit 30, but also a source program, a compressed program, an encrypted program, and the like.

  The communication control unit 61 is a modem for connecting the CPU 111 to the PSTN 7. The MFP 100 is assigned a telephone number in the PSTN 7 in advance. When a call is made from the facsimile apparatus connected to the PSTN 7 to the telephone number assigned to the MFP 100, the communication control unit 61 detects the call. When the communication control unit 61 detects a call, the communication control unit 61 establishes a call and causes the facsimile unit 60 to communicate.

  The facsimile unit 60 is connected to the PSTN 7 and transmits facsimile data to the PSTN 7 or receives facsimile data from the PSTN 7. The facsimile unit 60 outputs the received facsimile data to the CPU 111. The facsimile unit 60 converts the received facsimile data into print data that can be printed by the image forming unit 40 and outputs the print data to the image forming unit 40. As a result, the image forming unit 40 prints the facsimile data received by the facsimile unit 60 on a recording sheet. The facsimile unit 60 converts the image data stored in the HDD 116 into facsimile data, and outputs the facsimile data to a facsimile machine connected to the PSTN 7 or another MFP. As a result, the data stored in HDD 116 can be output to a facsimile machine or another MFP. The facsimile data is included in the image data. As described above, the MFP 100 has a facsimile transmission / reception function.

  The MFP 100 has a scanner function, and image data that the image reading unit 20 reads and outputs a document is temporarily stored in the RAM 112. The image forming unit 40 forms an image on a recording sheet such as paper based on image data output by the image reading unit 20 reading a document. Therefore, the MFP 100 has a copy function. Further, the data communication control unit 117 receives image data received from any of the other PCs 3, 3A, 3B, 3C connected to the network 2, or the digital camera 4 connected to the serial communication interface terminal 119, the digital video. Image data received from either the camera 5 or the portable information terminal 6 is temporarily stored in the RAM 112. Then, an image is formed on a recording sheet such as paper based on the image data temporarily stored in the RAM 112. Therefore, MFP 100 has a print function.

  The image processing unit 30 performs image processing on the image data stored in the RAM 112. When the MFP 100 activates the scanner function or the copy function, the image processing unit 30 performs image processing on image data output by the image reading unit 20 reading a document. Further, when MFP 100 activates the facsimile function, image processing unit 30 performs image processing on facsimile data (image data) received by facsimile unit 60. Further, the image processing unit 30 is connected to the image data received by the data communication control unit 117 from any of the other PCs 3, 3 A, 3 B, 3 C, scanner, and MFP connected to the network 2, or to the serial communication interface terminal 119. Image data received from any of the connected digital camera 4, digital video camera 5, and portable information terminal 6 is subjected to image processing.

  FIG. 4 is a diagram illustrating an example of a circuit configuration of the image processing unit. Referring to FIG. 4, an image processing unit 30 converts a resolution of image data to generate reduced image data, and a second conversion unit for binarizing the reduced image data to generate binarized data. 1 binarization unit 303A and second binarization unit 303B, a first recognition unit 305A and a second recognition unit 305B that extract a predetermined pattern from the binarized data, and a determination unit 307.

  The resolution converter 301 receives image data, converts the resolution of the input image data, and generates reduced image data. The image data defines positions and pixel values of a plurality of pixels arranged in a first direction (X-axis direction) and a second direction (Y-axis direction). The X-axis direction and the Y-axis direction are orthogonal to each other. The resolution conversion unit 301 converts the resolution by simply thinning out a plurality of pixels included in the image data, and generates a reduced image. Reduced image data is generated by simple decimation because reduced image data generated by other reduction methods, for example, smoothing, mixes the color of the surrounding pixels with the color of the pattern to be extracted. This is because the pixel color included in the data is different from the pattern color.

  Here, a specific example of resolution conversion processing will be described. For example, a case where image data with a resolution of 600 dpi (dots per inch) is converted into reduced image data with a resolution of 200 dpi will be described as an example. The resolution converter 301 includes two pixels in the X-axis direction from the image data. , And two pixels in the Y-axis direction are thinned out to generate a reduced image composed of a plurality of pixels. In other words, the image data is divided into blocks (three rows by three columns) consisting of three pixels in the X-axis direction and the Y-axis direction, and one pixel is extracted from each of the divided blocks. Reduced image data composed of the number of pixels included in the block is generated. The plurality of pixels included in the reduced image data have the same position in the block in which each pixel is included. Accordingly, when the resolution is converted from 600 dpi to 200 dpi, nine reduced image data can be generated. The resolution conversion unit 301 generates two reduced image data with different pixels extracted from the image data. Here, the two reduced image data generated by the resolution conversion unit 301 are referred to as first reduced image data and second reduced image data. The resolution conversion unit 301 outputs the first reduced image data to the first binarization unit 303A, and outputs the second reduced image data to the second binarization unit 303B.

  The plurality of pixels included in the first reduced image data and the plurality of pixels included in the second reduced image data have different positions in the image data. The relationship between the plurality of pixels included in the first reduced image data and the plurality of pixels included in the second reduced image data is that two pixels extracted from the same block of the image data are located in the pixel image data. It is preferable to have a relationship of 1 pixel to 2 pixels in the X-axis direction and 1 pixel to 2 pixels or less in the Y-axis direction. For example, when the first reduced image data is generated by extracting the pixels of 1 row and 1 column of each of a plurality of blocks of image data, the second reduced image data is converted into 2 rows and 2 columns of each of the plurality of blocks of image data, It is preferable to extract and generate any pixel in 2 rows, 3 columns, 3 rows and 2 columns, or 3 rows and 3 columns. That is, second reduced data obtained by extracting pixels in 2 rows and 2 columns of each of a plurality of blocks of image data, second reduced data obtained by extracting pixels in 2 rows and 3 columns, and second reduced data obtained by extracting pixels in 3 rows and 2 columns It is preferable to generate either data or second reduced data obtained by extracting pixels in 3 rows and 3 columns.

  The first binarization unit 303A and the second binarization unit 303B differ only in the reduced image data to be processed and have the same functions, and therefore, the first binarization unit 303A will be described here. The first binarization unit 303A receives the first reduced image data from the resolution conversion unit 301. The first binarization unit 303A binarizes the first reduced image data using two threshold values. In the case of image data obtained by reading a document with a pattern drawn on a striped background, the color of the pattern overlaps with the background stripe and the part where the pattern does not overlap with the background stripe Different. For this reason, the pixel where the pattern does not overlap the stripe pattern is binarized using the first threshold value, and the pixel where the pattern overlaps the stripe pattern is binarized using the second threshold value. Convert to value. The first threshold value is determined by the color of the pattern to be detected from the image data, and is a predetermined value. The second threshold value is determined by the color of the pattern and the color of the background pattern. The second threshold value may be a predetermined value, or may be calculated from the first threshold value and the background pattern color. For example, a value obtained by adding at least a part of the background pattern color value to the first threshold value may be used as the second threshold value. Here, a case will be described in which image data obtained by reading a document in which a pattern is drawn on a background of a horizontal stripe pattern is processed.

  The first binarization unit 303A performs binarization using the first threshold when there is even one white white pixel around the processing target pixel, and the white pixel exists around the processing target pixel. If none exists, binarization is performed using the second threshold value. This is because the background is often white. The peripheral pixels may be two pixels adjacent to the left and right (both sides in the first direction) of the pixel to be processed, for a total of four pixels. This is because the image data obtained by reading a document with a horizontal stripe pattern background has pixels that are not white pixels arranged in the left-right direction (X-axis direction).

  FIG. 5 shows a part of image data obtained by reading a document with a pattern drawn on a striped background. In the figure, one square indicates one pixel, and pixels indicated by numbers “2” or “3” indicate pixels constituting the pattern. Note that the numbers shown in the figure are given for the sake of explanation. The hatched pixels indicate the pixels forming the background stripe pattern. The pixel indicated by the numeral “2” is a pixel that constitutes a pattern and does not constitute a background stripe pattern. The pixel indicated by the numeral “3” is a pixel that forms a pattern and that forms a background stripe pattern. Therefore, the pixel indicated by the number “3” and the pixel indicated by the number “2” are not the same in density, and the density of the pixel indicated by the number “3” is the same as that of the pixel indicated by the number “2”. It becomes lower than the concentration. For this reason, it is impossible to extract the pixel indicated by the number “3” and the pixel indicated by the number “2” using one threshold value. Here, the pixel indicated by the number “2” constituting the pattern is extracted using the first threshold value, and the pixel indicated by the number “3” is extracted using the second threshold value. The pixel indicated by the number “1” and the pixel indicated by the number “2” are determined by determining whether a white pixel is present among a plurality of pixels adjacent in the horizontal direction (X-axis direction). Can be distinguished. In addition, when the background is a vertical stripe pattern, it can be distinguished by determining whether or not a white pixel exists among a plurality of pixels adjacent in the vertical direction (Y-axis direction).

  The image data includes three image data of red (R), green (G), and blue (B). For this reason, the first threshold value and the second threshold value define a range of pixel values for three of R, G, and B, respectively. If the pixel to be processed is a pixel that does not form a background stripe pattern, all the R, G, and B pixel values of the pixel to be processed are included in the range defined by the first threshold value. For example, it is determined that the pixel to be processed is a pixel constituting the pattern, and “1” is set to the value of the corresponding pixel in the binarized data. Conversely, if any one of the R, G, and B pixel values of the pixel to be processed is not included in the range defined by the first threshold value, the pixel to be processed forms a pattern. Therefore, “0” is set to the value of the corresponding pixel of the binarized data. Further, when the pixel to be processed is a pixel forming a background stripe pattern, all of the R, G, and B pixel values of the pixel to be processed are included in the range defined by the second threshold value. If it is determined that the pixel to be processed is a pixel constituting the pattern, “1” is set to the value of the corresponding pixel in the binarized data. Conversely, if any one of the R, G, and B pixel values of the pixel to be processed is not included in the range defined by the second threshold value, the pixel to be processed forms a pattern. Therefore, “0” is set to the value of the corresponding pixel of the binarized data.

  More specifically, the R pixel value of the pixel to be processed is included in the R range defined by the first threshold value or the second threshold value, and the G pixel of the pixel to be processed The pixel value of B of the pixel to be processed is included in the range of G defined by the first threshold value or the second threshold value, and the first threshold value or the second threshold value. If it is included in the range of B defined by the threshold value, it is determined that the processing target pixel is a pixel constituting the pattern. Otherwise, it is determined that the processing target pixel is not a pixel constituting the pattern. The image data may be monochrome data consisting only of brightness. In this case, each of the first threshold value and the second threshold value defines a range of brightness.

  Returning to FIG. 4, the first binarization unit 303A binarizes the first reduced image data to generate first binarized data. Then, the first binarized data is output to the first recognition unit 305A. In addition, the second binarization unit 303B binarizes the second reduced image data and generates second binarized data. Then, the second binarized data is output to the second recognition unit 305B.

  The first recognizing unit 305A and the second recognizing unit 305B have the same functions except that the binarized data to be processed is different, so the first recognizing unit 305A will be described here. The first recognizing unit 305A receives the first binarized data from the first binarizing unit 303A. The first recognition unit 305A receives a pattern to be extracted from the image data, and forms the pattern and a shape composed of a plurality of pixels having a pixel value “1” included in the first binarized data. Compare. If the shape of the pattern is similar to the shape composed of a plurality of pixels having a pixel value “1” included in the first binarized data, the first recognizing unit 305A Is output to the determination unit 307. If the two are not similar to each other, a signal indicating that the first binarized data does not include the pattern is output to the determination unit 307. Shape similarity includes similarity.

  The determination unit 307 receives a signal indicating that the first binarized data includes a pattern from the first recognizing unit 305A or the second binarized data from the second recognizing unit 305B. When a signal indicating inclusion is input, it is determined that the image data includes a pattern, and when a signal indicating no pattern is input from both the first recognition unit 305A and the second recognition unit 305B, image data Is determined not to contain a pattern, and the determination result is output to the CPU 111.

  Next, a specific example of image processing executed by the image processing unit 30 will be described. FIG. 6 is a diagram illustrating a part of image data as an example of image data. Referring to FIG. 6, similarly to FIG. 5, one square represents one pixel, and is image data including 36 pixels in the vertical and horizontal directions. Pixels indicated by the numbers “2” or “3” indicate pixels constituting the pattern. Numbers are given for explanation. The hatched pixels indicate the pixels constituting the background pattern. The background pattern is not arranged in the X-axis direction. The pixel indicated by the number “2” is a pixel that forms a pattern and does not form a background pattern. The pixel indicated by the numeral “3” is a pixel that forms a pattern and that forms a background pattern.

  7 to 9 are diagrams illustrating examples of reduced image data. FIGS. 7 to 9 show reduced image data generated by dividing the image data shown in FIG. 6 into 144 blocks each consisting of 3 pixels vertically and horizontally and extracting 1 pixel from each of 144 blocks. FIG. 7A shows reduced image data generated by extracting pixels in one row and one column of a block made up of three pixels in the vertical and horizontal directions. FIG. 7B shows reduced image data generated by extracting pixels in 2 rows and 1 column of a block composed of 3 pixels vertically and horizontally. FIG. 7C shows reduced image data generated by extracting pixels in 3 rows and 1 column of a block composed of 3 pixels vertically and horizontally. FIG. 8A shows reduced image data generated by extracting pixels in one row and two columns of a block made up of three pixels vertically and horizontally. FIG. 8B shows reduced image data generated by extracting pixels in 2 rows and 2 columns of a block composed of 3 pixels in the vertical and horizontal directions. FIG. 8C shows reduced image data generated by extracting pixels in 3 rows and 2 columns of a block composed of 3 pixels vertically and horizontally. FIG. 9A shows reduced image data generated by extracting pixels in one row and three columns of a block composed of three pixels in the vertical and horizontal directions. FIG. 9B shows reduced image data generated by extracting pixels in 2 rows and 3 columns of a block composed of 3 pixels vertically and horizontally. FIG. 9C shows reduced image data generated by extracting pixels in 3 rows and 3 columns of a block composed of 3 pixels vertically and horizontally. The values and hatching shown in the pixels of each reduced image data are the same as the values and hatching attached to the image data.

  10 to 12 are diagrams illustrating examples of binarized image data. FIG. 10A shows binary image data obtained by binarizing the reduced image data shown in FIG. 7A, and FIG. 10B shows the reduced image data shown in FIG. 7B. FIG. 10C shows binarized image data obtained by binarizing the reduced image data shown in FIG. 7C. FIG. 11A shows binary image data obtained by binarizing the reduced image data shown in FIG. 8A, and FIG. 11B shows the reduced image data shown in FIG. 8B. FIG. 11C shows binary image data obtained by binarizing the reduced image data shown in FIG. 8C. 12A shows binarized image data obtained by binarizing the reduced image data shown in FIG. 9A, and FIG. 12B shows the reduced image data shown in FIG. 9B. FIG. 12C shows binary image data obtained by binarizing the reduced image data shown in FIG. 9C. 10 to 12, pixels that are set to a value “1” by binarization are indicated by hatching.

  In the binarized image data shown in FIGS. 10A and 10B, the number of pixels set to “1” by binarization is smaller than the other binarized image data. This is because the pixels constituting the pattern represented by the value “2” or “3” included in the image data shown in FIG. 6 have been removed by the resolution conversion process and the binarization process. On the other hand, at least one of the nine binarized image data in FIGS. 10A to 12C, here, the pattern from seven reduced image data excluding FIGS. 10A and 10B. Can be extracted. For this reason, among a plurality of reduced image data that can be generated by resolution conversion, here, any one of the nine reduced image data in FIGS. 7A to 9C and the reduced image data. A pattern can be extracted from one of two pieces of reduced image data, which is another reduced image data having a predetermined relationship with the image data. The relationship between an arbitrary reduced image data and another reduced image data is such that another reduced image data is one or more in the X-axis direction and the Y-axis direction from the position in the image data of a plurality of pixels included in the arbitrary reduced image data. In addition, it is composed of a plurality of pixels separated by a predetermined number or less (here, 2 or less).

<Modification>
FIG. 13 is a diagram illustrating an example of a circuit configuration of the image processing unit in the modification. 4 differs from the circuit configuration shown in FIG. 4 in that the first binarization unit 303A and the second binarization unit 303B are changed to one binarization unit 303, the first recognition unit 305A and the second binarization unit 303B. The recognition unit 305B is changed to one recognition unit 305. The function of the binarization unit 303 is the same as that of the first binarization unit 303A and the second binarization unit 303B, and the function of the recognition unit 305 is the same as that of the first recognition unit 305A and the second recognition unit 305B. The same. Since the binarization unit 303 can process only one reduced image data, when the resolution conversion unit 301 generates the first reduced image data, the first reduced image data is converted into the binarization unit 303. Output to. When the recognition unit 305 extracts a pattern from the binarized data and outputs a signal indicating that the binarized data includes the pattern, the determination unit 307A determines that the image data includes the pattern, and the determination result Is output to the CPU 111. On the other hand, if the recognition unit 305 cannot extract a pattern from the first binarized data and outputs a signal indicating that the binarized data does not include a pattern, an instruction to generate the second reduced image data Is output to the resolution converter 301.

  The resolution conversion unit 301 generates reduced image data that is different from the first reduced image data that has been generated and output to the binarization unit 303, and outputs the reduced image data to the binarization unit 303. The relationship between the plurality of pixels included in the second reduced image data and the plurality of pixels included in the first generated reduced image data is that the two pixels extracted from the same block of the image data are The positions in the pixel image data are preferably 1 pixel to 2 pixels apart in the X axis direction and 1 pixel to 2 pixels apart in the Y axis direction.

  When the determination unit 307A extracts a pattern from the binarized data obtained by binarizing the second reduced image data and outputs a signal indicating that the binarized data includes the pattern, the image data Is included in the pattern, and the determination result is output to the CPU 111. On the other hand, when the recognition unit 305 cannot extract a pattern from the binarized data obtained by binarizing the second reduced image data and outputs a signal indicating that the binarized data does not include the pattern, the image data is It is determined that the pattern is not included, and the determination result is output to the CPU 111. This is because if the pattern is included in the image data, the pattern is included in one of the two reduced image data.

  FIG. 14 is a flowchart illustrating an example of the flow of image processing executed by the image processing unit. This image processing is processing executed by the image processing unit 30 when the image processing unit 30 executes the pattern extraction program stored in the ROM 113. Referring to FIG. 13, the image processing unit 30 determines whether image data has been received (step S01). The process waits until image data is received (NO in step S01). If image data is received, the process proceeds to step S02. That is, the image processing is processing that is executed by receiving image data. The image data is received by the image processing unit 30 reading the image data from the RAM 112 in accordance with an instruction from the CPU 111. Here, a case where image data including the portion shown in FIG. 5 is received will be described as an example.

  In step S02, the resolution of the image data is converted to generate reduced image data. Here, it is assumed that the reduced image data shown in FIG. In the next step S03, pattern matching processing is executed. As will be described later, the pattern matching process is a process for determining whether the reduced image data includes a pattern of a predetermined color and shape. The reason why the pattern matching process is executed on the reduced image data as a processing target instead of the image data itself is to reduce the amount of data to be processed and increase the processing speed.

  In step S04, it is determined whether the pattern has been extracted as a result of pattern matching. If the pattern can be extracted from the generated reduced image data in step S02, the process proceeds to step S07. If not, the process proceeds to step S05. In step S07, a signal indicating that there is a pattern is output to CPU 111, and the process ends. In step S05, it is determined whether or not the pattern matching process is executed twice. If the pattern matching process is executed twice, the process proceeds to step S08. However, the pattern matching process is executed only once and must be executed twice. If so, the process proceeds to step S06.

  In step S06, the pixel extracted from the image data in the resolution conversion process to be executed next is changed to a pixel different from the previously extracted pixel, and the process proceeds to step S02. Specifically, from the position in the pixel image data of the pixel extracted from the image data in the resolution conversion process executed earlier, the pixel is separated by 1 to 2 pixels in the X-axis direction and 1 to 2 pixels in the Y-axis direction. The pixel at the position is determined as the pixel to be extracted. In step S02, the pixel determined to be extracted in step S06 is extracted from the image data to generate reduced image data having a converted resolution. Then, pattern matching processing is performed on the generated reduced image data (step S03), and the process proceeds to step S04. In step S04, it is determined whether the pattern has been extracted as a result of pattern matching. In step S02, if the pattern can be extracted from the reduced image data generated for the second time, the process proceeds to step S07. If not, the process proceeds to step S05. When the process proceeds to step S05, since the pattern matching process has been executed twice, the process proceeds to step S08. This is because if the pattern is included in the image data, the pattern is included in one of the two reduced image data. In step S08, a signal indicating no pattern is output to CPU 111, and the process ends.

  Note that two reduced image data may be generated from the image data received in step S01, and step S03 and step S04 may be executed for each. That is, two pattern matching processes executed on two reduced image data are executed in parallel. Thereby, the processing speed can be increased. If any one of the reduced image data includes a pattern, the process proceeds to step S07. If neither of the two reduced image data includes a pattern, the process proceeds to step S08. In the two reduced image data, the position of the pixel extracted from the image data of one reduced image data and the position of the pixel extracted from the image data of the other reduced image data are one pixel or more in the X-axis direction. It is generated so as to be 2 pixels or less and 1 pixel or more and 2 pixels or less apart in the Y-axis direction.

  FIG. 15 is a flowchart illustrating an example of the flow of pattern matching processing. The pattern matching process is a process executed in step S03 of FIG. Referring to FIG. 15, in step S11, binarization processing for binarizing the reduced image data and generating binarized data is executed. Details of the binarization processing will be described later. Then, pattern recognition is performed to determine whether the binarized data includes a pattern. The pattern recognition result is determined (step S13), and if the binarized data includes a pattern, the process proceeds to step S14. If the binarized data does not include the pattern, the process proceeds to step S15. In step S14, “with pattern” is set as the return value, and the process returns to the image processing. In step S15, “no pattern” is set as the return value, and the process returns to the image processing.

  FIG. 16 is a flowchart illustrating an example of the binarization process. The binarization process is a process executed in step S11 of FIG. Referring to FIG. 16, in step S21, any one of a plurality of pixels included in the reduced image data is determined as a processing target pixel. Then, it is determined whether or not there are white white pixels around the pixel to be processed (step S22). Here, a total of four pixels, that is, a pixel to be processed and two pixels arranged on one side in the X-axis direction and two pixels arranged on the other side are used as peripheral pixels, and whether or not any of the peripheral pixels is a white pixel. Judging. If any one of the peripheral pixels is a white pixel, the process proceeds to step S23; otherwise, the process proceeds to step S26. If none of the peripheral pixels is a white pixel, it is highly likely that the processing target pixel is a background pattern pixel. If any one of the peripheral pixels is a white pixel, the processing target pixel is a background pattern pixel. It is likely not. This is because the threshold value used for binarization differs depending on whether the processing target pixel is a background pattern pixel or not.

  In step S23, it is determined whether or not the density of the processing target pixel is within the first range. Here, the first threshold is the first range. The first range is determined by the color of the pattern. When the image data is color, the first range is defined for each of R, G, and B. If the R, G, and B values of the processing target pixel are included in the ranges for R, G, and B defined in the first range, the density of the processing target pixel is determined to be within the first range, and the processing is performed. The process proceeds to step S24; otherwise, the process proceeds to step S25. In step S24, the pixel value of the binarized data corresponding to the processing target pixel is set to “1”, and the process proceeds to step S29. In step S25, the pixel value of the binarized data corresponding to the processing target pixel is set to “0”, and the process proceeds to step S29.

  In step S26, it is determined whether or not the density of the processing target pixel is within the second range. Here, the second threshold value is the second range. The second range is determined by the color of the pattern and the color of the background pattern, and defines the ranges for R, G, and B when the image data is color. If the R, G, and B values of the processing target pixel are included in the ranges for R, G, and B defined in the second range, respectively, it is determined that the density of the processing target pixel is within the second range, and the processing The process proceeds to step S27; otherwise, the process proceeds to step S28. In step S27, the pixel value of the binarized data corresponding to the processing target pixel is set to “1”, and the process proceeds to step S29. In step S28, the pixel value of the binarized data corresponding to the processing target pixel is set to “0”, and the process proceeds to step S29.

  As described above, MFP 100 according to the present embodiment generates reduced image data generated by thinning out a first number of pixels in the X-axis direction and thinning out a second number of pixels in the Y-axis direction from the image data. Since it is determined whether or not the binarized data obtained by binarizing includes a pattern, the number of pixels to be processed for pattern matching and the amount of data can be reduced to improve the processing speed.

  Further, the first reduced image data and the second reduced image data having different positions in the image data are generated, and any one of the first binarized data and the second binarized data obtained by binarizing them. Therefore, it is possible to improve the accuracy of pattern matching.

  Also, a plurality of pixels that are one or more and less than or equal to a predetermined number (here, two or less) in each of the X-axis direction and the Y-axis direction from a certain reduced image data and the position in the image data of a plurality of pixels included in the one reduced image data If the reduced image data consisting of is another reduced image data, if the image data includes a pattern, one of the reduced image data includes the pattern. For this reason, it is only necessary to determine whether or not the two reduced image data include a pattern, and the number of reduced image data to be processed can be reduced to improve the accuracy of pattern matching.

  In the above-described embodiment, the MFP 100 has been described as an example of the image processing apparatus. However, the pattern extraction method for causing the MFP 100 to execute the processes illustrated in FIGS. 14 to 16 and FIGS. It goes without saying that the invention can be understood as a pattern extraction program for causing the MFP 100 or the PCs 3, 3A, 3B, and 3C to execute processing.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

<Appendix>
(1) The image processing apparatus according to claim 3, wherein each of the first threshold value and the second threshold value defines a density range.
(2) The image processing apparatus according to (1), wherein a density that is the maximum value of the first threshold is higher than a density that is the maximum value of the second threshold.

1 is a diagram showing an overall outline of an image forming system in one embodiment of the present invention. 1 is a perspective view showing an appearance of an MFP. 2 is a block diagram illustrating an example of a hardware configuration of an MFP. FIG. It is a figure which shows an example of the circuit structure of an image process part. It is a figure which shows a part of image data obtained by reading a document with a pattern drawn on a striped background. It is a figure which shows a part of image data as an example of image data. It is a 1st figure which shows an example of reduced image data. It is a 2nd figure which shows an example of reduction image data. It is a 3rd figure which shows an example of reduced image data. It is a 1st figure which shows an example of binarized image data. It is a 2nd figure which shows an example of binarized image data. It is a 3rd figure which shows an example of binarized image data. It is a figure which shows an example of the circuit structure of the image process part in a modification. It is a flowchart which shows an example of the flow of the image process which an image process part performs. It is a flowchart which shows an example of the flow of a pattern matching process. It is a flowchart which shows an example of a binarization process.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 Image forming system 2 Network 3 3, 3A, 3B, 3C Computer 4 Digital camera 5 Digital video camera 6 Mobile information terminal 9 Operation panel 20 Image reading part 20 Image reading part 30 Image processing part 40 image forming unit, 50 paper feeding unit, 60 facsimile unit, 61 communication control unit, 100 MFP, 101 main circuit, 111 CPU, 112 RAM, 113 ROM, 114 display unit, 115 operation unit, 116 HDD, 117 data communication control , 118 LAN terminal, 119 serial communication interface terminal, 119A memory card, 301 resolution conversion unit, 303 binarization unit, 303A first binarization unit, 303B second binarization unit, 305 recognition unit, 305A First recognition unit, 305B Second recognition unit, 307, 3 7A determination unit.

Claims (6)

Image data acquisition means for acquiring image data defining positions and pixel values of a plurality of pixels arranged in a first direction and a second direction;
Reduction that generates a reduced image composed of a plurality of pixels by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the acquired image data. Image generating means;
The reduced image generating means generates a first reduced image and a second reduced image composed of a plurality of pixels whose positions in the image data are different from the plurality of pixels included in the first reduced image,
Binarization means for binarizing the generated first and second reduced images, respectively, and generating first and second binarized images;
An image processing apparatus comprising: a pattern matching unit that determines whether any of the first binarized image and the second binarized image includes a predetermined pattern.   In the image data, the reduced image generation means includes at least one of the plurality of pixels included in the first reduced image in the image data from the positions in the image data and the first direction and the first direction. The image processing apparatus according to claim 1, wherein the second reduced image including a plurality of pixels that are separated by a number or less is generated. The binarization means includes density detection means for detecting the density of pixels around the pixel to be processed;
First binarization means for binarization using a first threshold value when there is a white pixel having a density of the detected peripheral pixel equal to or lower than a predetermined density;
The image processing apparatus according to claim 1, further comprising: a second binarization unit that binarizes using a second threshold when the white pixel does not exist.   The image processing apparatus according to claim 3, wherein the density detection unit detects a density of pixels arranged in the first direction with respect to the processing target pixel. Receiving image data defining positions and pixel values of a plurality of pixels arranged in a first direction and a second direction;
By thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the received image data, a first reduced image composed of a plurality of pixels is obtained. Generating step;
Included in the first reduced image by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the received image data. Generating a second reduced image composed of a plurality of pixels whose positions in the image data are different from the plurality of pixels;
Generating first and second binarized images obtained by binarizing the generated first and second reduced images, respectively;
Determining whether at least one of the first binarized image and the second binarized image includes a predetermined pattern. Receiving image data defining positions and pixel values of a plurality of pixels arranged in a first direction and a second direction;
By thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the received image data, a first reduced image composed of a plurality of pixels is obtained. Generating step;
Included in the first reduced image by thinning out the first number of pixels in the first direction and thinning out the second number of pixels in the second direction from the received image data. Generating a second reduced image composed of a plurality of pixels whose positions in the image data are different from the plurality of pixels;
Generating first and second binarized images obtained by binarizing the generated first and second reduced images, respectively;
A pattern extraction program for causing a computer to execute whether or not at least one of the first binarized image and the second binarized image includes a predetermined pattern.

Images