JP2008181556A - Feature extraction method - Google Patents

Abstract

Provided is a feature extraction method capable of automatically and accurately extracting a feature of a sample even if it is an unknown sample.
An inspection light generator 30 irradiates inspection light toward a paper sheet sample held by a sample holder 23 in a main body 2 and images reflected light from the sample with an imaging device 50. Images acquired in a plurality of different wavelength bands are respectively acquired, and the calculation device 3 performs calculation according to a predetermined rule for these images to extract features. An image in which the features clearly appear is stored in the representative data storage unit 88 as a representative image. The image analysis unit 87 associates one of the appropriately set predicted feature images with each acquired image in the same manner, and repeats the process of correcting the predicted feature image in relation to each acquired image to thereby generate the predicted feature image. Converge, clarify features and classify.
[Selection] Figure 1

Description

  The present invention relates to a method for optically analyzing and extracting and classifying features of a sample to be inspected, particularly a paper surface of a paper sheet on which characters and design patterns are printed.

  For banknotes, securities, stamps, and other items that demonstrate the value of exchange using paper as a medium, distinguishing authenticity has always been a major issue, and what is the characteristic of the paper sheet when distinguishing authenticity? It is necessary to properly grasp this.

  In recent years, color copiers, color printers, scanners, etc. have been improved in performance and reduced in price, and it has become easy to induce counterfeiting of paper sheets. For this reason, markings that are not included in commercially available color copying toners and printer inks, such as fluorescent materials and other functional materials, are performed under normal lighting conditions and invisible to the naked eye. . These markings naturally constitute the characteristics of paper sheets.

  In the paper sheet authenticity identification device described in Patent Document 1, ultraviolet light is applied to a specific part of the paper to be identified, and transmitted light or reflected light from the ultraviolet light irradiation part is applied to a wavelength selection filter to emit light in a specific wavelength band. Only the photo sensor array receives light, identifies the authenticity of the paper quality of the paper to be identified based on the light output signal of the photo sensor array, identifies the authenticity of the fluorescent substance that generates fluorescence by ultraviolet irradiation, and both identification results Is true, the identified paper is true.

  The paper sheet authenticity discrimination device discriminates whether or not the paper used for the paper sheet is genuine by the light output signal of the photosensor. However, since this apparatus is for confirming the already recognized optical characteristics and not for checking the printed figure on the paper, it is difficult to say that it is a perfect method for authenticating paper sheets.

  In the document inspection apparatus described in Patent Document 2, at least two light portions having different wavelengths are directed on a common area of a document, and reflected light or transmitted light is detected by a linear detector.

  The document inspection apparatus can use a printed figure as an inspection standard. Further, reflected light or transmitted light is detected by a plurality of detectors, and signals coming from the detectors are evaluated alone or in an appropriate combination, and multifaceted inspection is possible. However, it is difficult to say that sufficient technical pursuit has been made as to how data obtained by a plurality of detectors are related and processed to improve the function of the inspection apparatus.

  Patent Document 3 discloses an apparatus for optically inspecting a banknote based on a characteristic color tone of the banknote. In the inspection, a specific surface of the banknote is irradiated with light emitted from a wide area light source. The reflected light is dispersed into various wavelength ranges by an optical scattering mechanism, for example, a glass prism. The brightness of the colors present in the various wavelength ranges is recorded with several associated photoelectric detectors. The measured signal is evaluated at the threshold level, and if the measured value is within the allowable range, an OK signal is obtained.

  In the case of the above-mentioned apparatus, only the wavelength specified by the photoelectric detector planned in advance can be detected, so that it is not suitable for analysis of paper sheets whose optical characteristics are unknown. Further, since the area to be inspected is also a spot, it cannot be analyzed as an optical image.

A known spectrophotometer or the like measures optical characteristics in a wide wavelength range, but the measurement area is a spot, and it is difficult to inspect the characteristics of the entire area of the paper. An apparatus for measuring the optical characteristics of the entire paper surface with a CCD camera or the like is also well known, but the search wavelength band is as narrow as 400 to 1,000 nm, and only a large number of captured images are obtained. In these methods, enormous effort and time are required to extract the characteristics of the sample from a large number of paper optical characteristic images corresponding to each wavelength light, and each of the paper image information is complicated, and the search conditions of the light emitting and receiving are detailed and detailed. Sample feature detection was difficult and incomplete.
JP 2001-52232 A JP-A-4-288977 Swiss Patent No. 476356

  An object of the present invention is to provide a feature extraction method capable of automatically and accurately extracting a feature of a sample even if it is an unknown sample.

  The feature extraction method of the present invention selectively irradiates a sample with light in a wavelength region ranging from the ultraviolet region to the near infrared region as a whole wavelength region light or multiple wavelength band light having different center wavelengths as inspection light. A plurality of captured images are obtained by sequentially capturing the light from the sample for each of the irradiated inspection lights for each predetermined wavelength band having a different center wavelength, and the optical image of the sample is obtained from these captured images. Compares the degree of approximation between the first step of setting a plurality of predicted feature images as index data for similar classification processing and the plurality of predicted feature images for each of the plurality of captured images. However, the second step of sequentially correcting the most similar predicted feature image to be similar to the captured image as having the similar relationship, and the correction of the predicted feature image to the similar captured image is made smaller than the previous time, and By repeatedly carrying out the two steps, and is intended to include a third step of gradually converge each feature image as a representative image of the captured image in a similar relationship, the.

  According to this configuration, the sample is selectively irradiated with light in a wavelength region ranging from the ultraviolet region to the near infrared region as the entire wavelength region light or the inspection light of a predetermined wavelength band having a different central wavelength. For each inspection light, light from the sample is sequentially imaged for each predetermined wavelength band having a different center wavelength to obtain a plurality of captured images. Therefore, the wavelength band of the irradiation light (or the center of the wavelength band) Wavelength) and the wavelength band of the imaging light (or the center wavelength of the wavelength band), or a predetermined rule for a plurality of captured images captured while changing one of the wavelength bands (center wavelength of the wavelength band). Based on this, it is possible to extract and classify the features, and automatically narrow down the features of the sample from among the number of images as the base optical characteristics. Furthermore, by acquiring a large number of optical characteristic captured images over a wide wavelength range, the characteristics of the sample can be extracted and classified reliably and accurately.

  The first step of setting a plurality of predicted feature images as index data for the similar classification process and the predicted feature that is most approximated by comparing the degree of approximation with the plurality of predicted feature images for each of the plurality of captured images A second step of sequentially correcting the images so as to be close to the captured image as being in a similar relationship, and a correction to the similar captured image of the predicted feature image is made smaller than the previous time, and the second step is repeatedly performed, A third step of gradually converging each feature image as a representative image of a similar captured image, so that each predicted feature image is gradually converged for each group of similar captured images, It can be clarified. As a result, even if there are a large number of basic captured images, they can be efficiently classified into similar categories to obtain these representative images. A representative image can be revealed.

  According to the present invention, in the feature extraction method configured as described above, if there are captured images that are not included in a predetermined approximate range for any of the predicted feature images converged among the plurality of captured images, A new predicted feature image is created using the captured images.

  According to this configuration, a characteristic image is not classified in the same manner as another predicted characteristic image, and the characteristic is properly grasped and classified without being ignored.

  Further, according to the present invention, in the feature extraction method having the above-described configuration, when the predicted feature image that is not similar to any of the plurality of captured images is generated, the predicted feature image is deleted. As a result, memory is not consumed for meaningless data, and feature extraction and classification can be performed appropriately even when the initial predicted feature image is excessively set.

  In the present invention, the distance between the converged predicted feature images is within a predetermined value, and the maximum distance between the captured images corresponding to each of the predicted feature images is within a separately set value. These predicted feature images are integrated and updated to their average values. As a result, when a plurality of predicted feature image groups exist within a predetermined approximate value, since they are integrated as a single predicted feature image group of the average value data, more predicted feature image groups than necessary The captured images to be processed are grouped for each representative image with a predetermined similarity, and the features are classified into the same category.

According to the present invention, these representative images can be obtained by classifying them efficiently even if there are a large number of underlying captured images.

  Embodiments of the present invention will be described below with reference to the drawings. First, the structure of a feature extraction apparatus that performs the feature extraction method of the present invention will be described with reference to FIGS.

  The feature extraction device 1 includes a main body 2 and an arithmetic device 3. The main body 2 has a housing 10, and its internal components are divided into an optical section 11 and a control section 12 as shown in FIG. 1 to 6 show the components included exclusively in the optical section 11.

  The housing 10 of the main body 2 is supported by a plurality of casters 21 so as to be movable on the floor surface. A part of the housing 10 has a door 22, and the sample holder 23 is taken in and out by opening the door 22. If the door 22 is closed, the inside of the housing 10 is in a dark room state. The sample holder 23 holds a paper sheet sample to be inspected so that the surface to be inspected is substantially vertical. The surface to be inspected is irradiated with inspection light, and reflected light (including excitation light of the fluorescent material, if any) is imaged. Next, the configuration of the inspection light generator 30 and the imaging device 50 will be described.

  The light source unit 31 of the inspection light generator 30 emits light in the wavelength range of 250 to 2,000 nm. Since such a wide band of light cannot be generated by a single lamp, two types of lamps, a xenon lamp 32 and a halogen lamp 33 are used (see FIGS. 4 and 5). The xenon lamp 32 is used for obtaining inspection light of 250 to 380 nm, and the halogen lamp 33 is used for obtaining inspection light of 381 to 2,000 nm.

  The xenon lamp 32 and the halogen lamp 33 are disposed facing each other in the lamp house 34. Since it takes time for the lamp to emit light of the specified spectrum after the power is turned on, both lamps are lit continuously while the device is in operation, instead of turning the lamp on and off each time the lamp is switched. In addition, the light on the required side is selectively reflected by the movable mirror each time. Reference numeral 35 denotes the movable mirror, and the reflection surface is directed to the xenon lamp 32 at a 45 ° angle, and the reflection surface is directed to the halogen lamp 33 at a 45 ° angle in FIG. It is switched by a motor or solenoid (not shown). The light hitting the movable mirror 35 turns at a right angle and enters the lens house 37 through the exit window 36 on one side of the lamp house 34.

  The light whose divergence angle is adjusted by the lens group in the lens house 37 enters the spectroscope 38. The spectroscope 38 is an aberration-correction type zero dispersion double monochromator. The drive wavelength range is set to 250 to 2,000 nm, the half-value width is set to 30 nm or 60 nm, and the resolution is set to 15 to 30 nm. It can also be set to “white light including the entire wavelength range”. Light of a predetermined wavelength band emitted from the spectroscope 38 becomes inspection light.

  A lens house 39 is connected to the exit window of the spectroscope 38. A lens (not shown) disposed in the lens house 39 is for adjusting the divergence angle of the inspection light, and is similarly 50 × 50 mm when irradiating an area of 180 × 180 mm on the sample holder 23. The divergence angle is switched between when irradiating the area.

  The inspection light exiting the lens house 39 travels through the space while being repeatedly reflected by the fixed mirrors 40 and 41, and irradiates the sample held by the sample holder 23. Light reflected and absorbed by the surface to be inspected of the sample enters the imaging device 50. The sample holder 23 is set so that the irradiation angle and the reflection angle of the sample become an angle that minimizes image distortion as much as possible.

  As described above, the inspection light band ranges from 250 to 2,000 nm. However, there is no imaging means having a wide sensing area, so the imaging apparatus 50 is configured with two types of cameras. One of them is a CCD camera 51, which is arranged in front of the sample holder 23 as seen in FIGS. The other is an infrared camera 52, which is arranged in parallel with the CCD camera 51 at a position shifted in the horizontal direction from the front in front of the sample holder 23.

  A CCD camera 51 having an imaging element made of silicon or the like is used for imaging reflected light having a wavelength of 250 to 1,000 nm. An infrared camera 52 having an imaging element made of platinum indium, indium antimony, or the like is used for imaging reflected light of 1,000 to 2,000 nm. These cameras have about 65,000 (≈256 × 256) pixels to about 1 million (≈1024 × 1024) pixels or more, and the sample surface to be analyzed is 16384 to 65536 gradations. The image is captured and input as the above-described grayscale fine image.

  The camera is switched by the movable mirror 53 shown in FIGS. The movable mirror 53 is moved in the horizontal direction by a driving mechanism (not shown). When the movable mirror 53 reaches the position shown in FIG. 2, the reflected light from the sample holder 23 reaches the CCD camera 51 straight. When the movable mirror 53 reaches the position shown in FIG. 3, the reflected light is bent at a right angle by the movable mirror 53 and is bent again at a right angle by the fixed mirror 54 and reaches the infrared camera 52.

  Reference numerals 55a, 55b, 56a and 56b denote converging lenses which appear and disappear in respective optical paths between the sample holder 23 and the CCD camera 51, and the fixed mirror 54 and the infrared camera 52 by a driving mechanism (not shown). The converging lenses 55a and 56a are used when converging the reflected light when the irradiation area is 180 × 180 mm, and the converging lenses 55b and 56b are used when converging the reflected light when the irradiation area is 50 × 50 mm. Use.

  In FIGS. 1, 2, and 3, the converging lenses 55a and 55b are shown in the optical path so that the combination of the converging lenses 55a and 55b or the converging lenses 56a and 56b exist at the same time. Actually, only one of the combinations advances into the optical path, and the other one is retracted out of the optical path.

  Since the light receiving area and / or image forming position on the CCD or infrared imaging device slightly changes between when the converging lenses 55a and 56a are used and when the converging lenses 55b and 56b are used, these cameras 51 are driven by a driving mechanism (not shown). , 52 are moved along the optical axis to compensate for the change. A zoom lens mechanism may be used instead of moving the camera.

  In order to narrow down the imaged light to a predetermined wavelength range, the CCD camera 51 is combined with a spectroscope (ultraviolet visible image spectroscope) 57, and the infrared camera 52 is combined with a bandpass filter (near infrared bandpass filter) 58. It is done. The spectroscope 57 has a half width of 30 nm and a resolution of 15 nm. The band pass filter 58 has a half width of 30 to 60 nm and a resolution of 30 nm. The spectroscope 57 and the band-pass filter 58 also have a function of selecting light in the entire wavelength range in the same manner as the spectroscope 38 on the light source side.

  FIG. 6 shows a structural example of the band pass filter 58. This is a combination of three turrets 59a, 59b and 59c, each of which is index rotated by a motor (not shown). Each turret 59a, 59b, 59c holds 13 filter holders 60 radially, and each one filter holder 60 is made to coincide with the optical path. In FIG. 6, a hatched circle (circle represents a filter) indicates the position of the optical path.

  Of the 13 filter holders 60 held by the turrets 59a, 59b, and 59c, the filter 61 having a slightly different pass wavelength band is attached to 12 of the filter holders 60, and the remaining one is transparent for the entire wavelength range. . If the filter holder 60 through which the turrets 59b and 59c pass is selected, the 12 types of filters of the turret 59a can be used alone. If the transparent filter holder 60 is selected by the turrets 59a and 59c, the 12 types of filters of the turret 59b can be used alone in the same manner. If the transparent filter holder 60 is selected with the turrets 59a and 59b, the 12 types of filters of the turret 59c can be used alone as well. Further, if the filter holder 60 that is transparent in all of the turrets 59a, 59b, and 59c is selected, light in the entire wavelength band is selected.

  Next, a block configuration of the feature extraction apparatus 1 will be described with reference to FIG.

  The control section 12 of the main body 10 includes a lamp controller 70, a mirror controller 71, a lens controller 72, an irradiation side spectrometer controller 73, an imaging side spectrometer controller 74, and a camera controller 75. The lamp controller 70 controls turning on / off of the xenon lamp 32 and the halogen lamp 33. The mirror control unit 71 controls the operation of the movable mirrors 35 and 53. The lens control unit 72 controls the operation of the lenses in the lens house 39 and the converging lenses 55a, 55b, 56a, and 56b. The irradiation side spectroscope control unit 73 controls the operation of the spectroscope 38. The imaging side spectroscope control unit 74 controls the operation of the spectroscope 57 and the band pass filter 58. The camera control unit 75 controls the exposure time and other shooting condition settings and imaging of the CCD camera 51 and the infrared camera 52.

  The block configuration of the arithmetic device 3 is as follows. A central processing unit 80 includes a microprocessor and a storage device. Reference numeral 81 denotes an operation unit, which includes input means such as a keyboard and various switches provided on the main body of the arithmetic device 3. A display unit 82 includes a monitor such as a CRT or a liquid crystal and a display unit such as a light emitting diode provided in the main body of the arithmetic unit 3. The arithmetic device 3 and the main body 2 are connected by a cable (not shown) and exchange signals with each other.

  Reference numerals 83 to 88 denote data processing block groups configured by using system resources of the central processing unit 80 as they are or adding hardware elements to the system resources of the central processing unit 80. Reference numeral 83 denotes an A / D converter, which converts analog data of an image transmitted from the imaging device 50 into digital data. 84 controls the CCD camera 51 and the infrared camera 52 appropriately, unifies the image data obtained by the CCD camera 51 and the image data obtained by the infrared camera 52, and cuts out as an input image of a necessary size that is separately selected and set. At the same time, the correction calculation unit compresses the image size. A correction data storage unit 85 stores parameters such as calculation coefficients for the correction calculation unit 84 to perform calculation. Reference numeral 86 denotes an image buffer unit that holds an image cut out to the required size, a compressed image, and a temporary intermediate image that is processed for image feature extraction. Reference numeral 87 denotes an image analysis unit for extracting features, and reference numeral 88 denotes a representative data storage unit that stores a representative image and related data selected as having clear features.

  Next, the operation of the feature extraction apparatus 1 will be described. First, the door 22 of the main body 2 is opened, the sample holder 23 is taken out, and a sample to be inspected is attached. The sample holder 23 to which the sample is attached is set at a predetermined position in the housing 10 and the door 22 is closed. Then, the sample is irradiated with the inspection light, and the light reflected from the sample is imaged by the imaging device 50.

  The inspection light generator 30 uses light in a wide wavelength range from 250 to 2,000 nm ranging from the ultraviolet region to the near infrared region as all-wavelength region light (white light) or as inspection light in a predetermined band while shifting the center wavelength at a predetermined pitch. Selectively occurs sequentially. The sample surface looks according to the inspection light. For example, when a fluorescent material is contained in the material constituting the paper or in the printing ink, the fluorescent material emits excitation light in response to the inspection light having a specific wavelength. The light image obtained by combining the excitation light and the reflected light is passed through the spectroscope 57 or the band pass filter 58, and is picked up by the CCD camera 51 or the infrared camera 52 as a grayscale image of specific wavelength light.

  FIG. 8 illustrates the transition of the image of the paper sheet when the spectroscope and the bandpass filter on the camera side are passed through while shifting the wavelength range of the inspection light to be irradiated, that is, the image is captured as light in the entire wavelength range. In (a), the original pattern of the paper sheet is not seen at all, and the pattern due to the excitation of the fluorescent material is only visible in the lower right. As the wavelength of the inspection light becomes longer as (b) → (c) → (d) → (e) → (f), the original visual visible light pattern of the paper sheet gradually appears and the excitation light pattern disappears. In (g), the original pattern of the paper sheet forms the clearest and brightest image. Thereafter, as the wavelength of the inspection light increases from (h) → (i) → (j) → (k), the image loses clarity and brightness. In (l), only a pattern sensitive only to the near infrared is visible.

  Note that FIG. 8 is merely a drawing example simplified for explanation, and an actual image does not follow the same transition. An image group obtained by imaging an actual paper sheet over a wavelength range of 250 nm to 2,000 nm shows much more complicated changes.

  As described above, the inspection light generation device 30 irradiates a plurality of types of light having different wavelengths in a stepwise manner and a narrow band as the inspection light, or light of all wavelengths (white light). The central wavelength of the inspection light is set to 86 steps between 250 and 2,000 nm (one of which is light in the entire wavelength range). Assuming that the pass wavelength band of all of the wavelengths is set, 86 × 86 = 7,396 images are captured.

  The CCD camera 51 and the infrared camera 52 have their own light sensitivity characteristics. FIG. 9 conceptually shows this. The imageable wavelength bands of both cameras overlap in the vicinity of 1,000 nm, and the two cameras are switched and used with the switching point being 1,000 nm. However, at the switching point as it is, the image brightness and the density gradient are completely different between the image captured by the CCD camera 51 and the image captured by the infrared camera 52. If this is the case, there are two types of image data under the same conditions, and the image processing software and the data storage unit are dualized, and the system resources of the arithmetic device 3 are consumed extra.

  Therefore, one or both cameras are set so that the degree of approximation of the captured images of the CCD camera 51 and the infrared camera 52 at the switching point is equal to or higher than a predetermined level, that is, as if the single camera is picked up across the switching point. Correct. Specifically, the brightness of the image is corrected by adjusting the exposure time of the camera, and the density gradient is corrected by adjusting the sensitivity and gain. Only one or both of the brightness and the density gradient may be corrected. Since it is desirable that the imaging characteristics be flat even if the switching point is separated, correction is performed at each wavelength level. FIG. 10 conceptually shows the correction performed here.

  To correct the brightness and density gradient of the image, a bright reference point and a dark reference point are set in advance on a part of the imaging surface, and the brighter reading values of both cameras are brighter and the darker one is darker. On the other hand, it is necessary to correct the necessary light and dark area (dynamic range) to 256 gradations for calculation so as to be the same level. In determining the reference point, one of the following two methods is used.

  In the method shown in FIG. 11, a reference point is set in the sample image itself. Reference numeral 90 is an image of the sample, and reference points 91 and 92 are set in a bright part and a dark part, respectively. When the reference points 91 and 92 of the image captured by the CCD camera 51 and the reference points 91 and 92 of the image captured by the infrared camera 52 are compared, the brightness and density gradient of both images are close to a predetermined level or higher. The camera control value is corrected.

  In the method shown in FIG. 12, a light / dark reference plate arranged on the sample holder 23 of the apparatus is used. That is, the brighter reference plate 93 and the darker reference plate 94 are mounted in a place where they are in the imaging area and are not covered by the paper sheet sample, and the images of the reference plates 93 and 94 are also captured together with the sample image. . Based on the image values of the reference plates 93 and 94, the camera control value is corrected in the same manner as described above.

The light accumulation time adjustment can be realized by using a CCD having a so-called variable time shutter function. In addition, a physical element in which a film of transition metal oxide (IrOx, Ta ₂ O ₅ , WO ₃ etc.) is formed on the glass plate surface is placed in front of the CCD, and a voltage is applied to the physical element to apply the light to the film. The transmittance or light transmission amount may be adjusted. For this adjustment, a setting table of applied voltage or shutter opening time used for each imaging wavelength is prepared in advance.

  By correcting the camera control value in this way, the image processing software and the data storage unit can be unified, and system resources can be saved and the processing speed can be increased. In addition, when the brightness and / or the density gradient are additionally corrected with different accuracy as required, accurate calculation processing is possible because the original captured images are approximated. Parameters such as calculation coefficients for performing the correction calculation are stored in the correction data storage unit 85.

  Now, it is possible to acquire a large number of images with different imaging wavelength bands by the feature extraction apparatus 1. For example, all the minute image data in which each pixel is composed of about tens of thousands of shades and about 1 million pixels are stored in the paper sheet. When it is handled as a feature image of a kind, a large amount of memory is required, and it takes time to collate if a lot of data is stored as a feature when extracting features of the same kind of paper later. Too much.

  In addition, even if the same type of sample is used, it is not always the same printed state due to misalignment or fading, and if used, dirt components such as fading and sebum will occur, resulting in differences in the captured images. Can occur, and even samples of the same type can be rejected as counterfeit tickets. Therefore, except for extremely fine high-accuracy feature searches, the features to be extracted are compressed to a certain extent, while maintaining the fine and fine optical characteristics, and the allowable range by compressing the image size and / or the gradation level. It is better to have

  Therefore, the arithmetic device 3 performs a similar classification operation based on feature extraction according to a predetermined rule for each of the cut image and / or the compressed image cut into a plurality of necessary sizes input to the image buffer unit 86, and the paper sheet. An image that clearly shows the characteristics of the class is stored in the representative data storage unit 88 as representative data. Hereinafter, a calculation method for automatically extracting features will be described.

  A first method relating to feature extraction and similar classification of paper sheets uses a difference between images to be classified. FIG. 13 shows the concept of analysis by difference. That is, pay attention to the difference in data between one image and another image. If the first image has “ABCDEF” data and the second image has only “ABDEF” data, the difference between them is “C”. Characteristic analysis is performed using the difference “C” as a material.

  As difference data, a difference value (difference value) for “brightness” for each pixel corresponding to each image and the frequency of each difference value (data number for each difference value) are obtained. “Brightness” means “bright” means that the amount of reflected light and / or excitation light is large in the imaged wavelength band. That is, the characteristic pattern that should appear in the imaging wavelength band appears more clearly. “Bright” can be rephrased as “dark”. Conversely, “darkness” represents the light absorption characteristic. “Frequency” indicates the number of pixels having the difference value.

  Subsequent calculations are performed using AD values of 256 tones obtained by converting the brightness of actual pixels into digital values. Accordingly, the difference value of “brightness” between the two images is replaced with one of the AD values of −255 to +255 as shown in FIG.

  In the calculation, the product sum of each AD value and the frequency is obtained and then the sum of the products is obtained. Regarding the method for obtaining this product, a method of obtaining the product of the frequency and the AD value with a positive / negative sign attached ( The example shown in FIG. 14 corresponds to this) and the method of obtaining the product of the “index” that is the absolute value of the AD value and the frequency (the example shown in FIG. 15 corresponds to this). The sum of the former products is referred to as “product sum”, and the sum of the latter products is referred to as “exponential sum”.

  When the calculation is performed using an exponent, the difference difference is further emphasized in order to facilitate the calculation. FIG. 15 shows an example of the method. In FIG. 15, the absolute value of the difference value is obtained, and a value obtained by further subtracting “a constant value” is used as a “difference value index”. If a negative value appears, this is set to “zero”.

  In FIG. 15, “constant value” is separately set to “30”, so that the interval from −30 to +30 in the difference value is all “zero” in the difference value index as the noise component region. That is, all pixels (pixels) having a difference value of −30 to +30 are treated as the same image within the allowable error range. Therefore, the influence of noise between approximate images is eliminated, and only pixels with a true difference that have a difference value of ± 30 or more are configured to be recognized as separate images. FIG. 16 is a graph showing the relationship between the difference value and the index.

A method of extracting features based on the difference values and selecting an image that clearly represents the features as a representative image will be described with reference to FIG. FIG. 17 shows eight images. These images are picked up for each wavelength band with different center wavelengths at a predetermined pitch, and are arranged in order of wavelength. The image P _i-4 is low in brightness, and gradually increases as it approaches P _i-3 , P _i-2, and P _i , and reaches a peak in the image P _i . After the image P _i , the brightness decreases gradually to the image P _{i + 3} . That is, an example is shown in which a person image gradually emerges from a black image, and then gradually fades out to return to a black image. It is self-evident that the same is true in the case of light and dark, and the description is omitted.

Sum of products of the frequencies corresponding thereto and each difference value index between adjacent images (sum of products) represented by D _i. A change from “low brightness” to “high brightness” is expressed as “plus” and vice versa. The product sum D _i indicates the amount of difference between the contrasted images.

  Described below is a representative image selection processing procedure in the case where the above-mentioned exponent sum is smaller than a separately determined threshold value and is determined to be a similar image.

Image P _i-4 and P _i-3, P _i-3 and P _i-2, P _i-2 and P _i-1, P _i-1 are both the product-sum D _i between the P _i "plus In other words, it is in the area where the figure of the person appears. However, when it is between the images P _i and P _{i + 1} , the product sum D _i turns to “minus”, that is, the fade-out area of the human image, and the images P _{i + 1} and P _{i + 2} , P _{i + 2} and P _{i +.} Keep “minus” during ₃ . This is because the trend of shifting from “low brightness” to “high brightness” was reversed between the image P _i and the image P _{i + 1} , and thus the images P _i and P _{i Between +1} is the changing point.

The image P _i located immediately before the change point is the brightest and clearest among the preceding and following image groups. That because the feature common to the image group in which appeared the most easy identification form, before and after the image P _i-4 of the image P _i as well as employing the same as the representative image, P _i-3 ... P _{i + 4} is stored and registered in the representative data storage unit 88 as a similar image.

  Next, a representative image selection processing procedure in the case where it is determined that the above-mentioned exponent sum is larger than a separately determined threshold value and is not a similar image will be described.

In FIG. 18, the group 1 image group that has changed from “low brightness” to “high brightness” has suddenly changed to an image group 2 that is not similar between the images P _i and P _{i + 1.} Indicates the case. In this case, the exponent sum is larger than a separately defined threshold value. At this time, as described above, the brightest last image P _i in the group 1 image group is registered as the representative image. In the images P _i-4 , P _i-3 , P _i-2 , P _i-1 , only information is stored and registered in the representative data storage unit 88 as similar images.

  The above operation is repeated, and several types of representative images and their similar images are extracted from a large number of image groups acquired over a wavelength range of 250 to 2,000 nm, and stored and registered in the representative data storage unit 88 together with similar image information.

  In this way, optical features are automatically extracted from one sample, and images that clearly represent the features are sorted and stored as representative images. This series of image analysis is performed according to the flowchart of FIG. Carried out.

  In step S101 in FIG. 19, a difference value for each pixel between the “current image” and the “previous image” is obtained for all the pixels. The “current image” is the analysis image that is currently being analyzed, and the “previous image” is the analysis image that was analyzed immediately before. It is assumed that the “previous image” has already been found to be similar to any one of the representative images. In step S102, the sum of products of the difference value index emphasizing the value of the difference value obtained by the method of FIG. 15 and the frequency for each difference value index is obtained as the index sum. In step S103, it is determined whether the exponent sum is equal to or greater than a predetermined threshold value. If the predetermined threshold value has not been reached, that is, it is determined that the current image is similar to the previous image, and the process proceeds to step S104.

  In step S104, it is determined whether or not the current image is “brighter” than the previous image. As described above, “bright” means that the amount of reflected light and / or excitation light is large in the imaged wavelength band. That is, the characteristic pattern that should appear in the imaging wavelength band appears more clearly. In the “brightness” comparison, not the exponent sum but the sum of the products of the difference value and the frequency with the sign of positive and negative (product sum in FIG. 14) is used (the same applies to steps S105 and S106).

  If the current image is brighter than the previous image, the process proceeds to step S105. Here, a difference value for each pixel between the representative image having the same relationship as the previous image and the current image is obtained over all the pixels, and the brightness is compared. As a result, if it is determined in step S106 that the current image is brighter than the representative image by a predetermined value or more, the process proceeds to step S107.

  In step S107, the representative image of the similar group is updated, the current image is made a new representative image, and the image that has been the representative image so far is registered as a similar image of the new representative image.

  If the current image is not brighter than the previous image in step S104, the process proceeds to step S108. Then, it is registered as being similar to the representative image up to the previous time.

  In step S106, the process also proceeds to step S108 when it is determined that the current image is not brighter than the representative image by a predetermined value, that is, in the error range. Then, it is registered as being similar to the representative image up to the previous time.

  On the other hand, if it is determined in step S103 that the exponent sum is equal to or greater than the predetermined threshold, the current image and the previous image are dissimilar, and the process proceeds to step S109.

  In step S109, all the representative images registered so far and / or in the feature extraction process of this sample and the current image are collated with the sum of products to find the minimum difference representative image as the most approximate image, and the process proceeds to step S110. .

  In step S110, the minimum difference representative image is temporarily set as the representative image of the current image, and a difference value for each pixel between the temporary set representative image and the current image is obtained for all pixels. In step S111, the sum of the products of the difference value index emphasizing the difference value obtained by the method of FIG. 15 and the frequency for each index is obtained as the index sum. In step S112, it is determined whether the exponent sum is equal to or greater than a predetermined determination value. If the predetermined determination value has not been reached, the process proceeds to step S105 on the assumption that the minimum difference representative image as the temporary representative is similar to the current image, and the same processing as described above is executed.

  If the index sum is greater than or equal to the predetermined determination value in step S112, the process proceeds to step S113 on the assumption that the minimum difference representative image as the temporary representative and the current image are dissimilar. The current image is registered as a new representative image.

  As for the image data, the detailed image data used for the feature extraction calculation is left for the representative image. For images other than the representative image, only the collation data (classification information such as optical characteristic feature extraction conditions) with the representative image is left, and the image data itself can be erased. This makes it possible to save the amount of memory spent on one sample.

  Furthermore, although not shown in the figure, the feature extraction apparatus 1 is configured to store and hold a read image (camera image) from the camera corresponding to the representative image as a representative real image. In other words, even if the difference value calculation of the preceding and following images and other classification sorting operations are simply performed at high speed based on the separately set compressed image data, detailed camera image data is retained as it is as a representative real image. When re-sorting calculation is performed according to another calculation specification, it is possible to perform highly accurate feature extraction from each representative actual image data and collation data.

  When it is necessary to distinguish between different samples using these extraction features, a new sample is imaged for each wavelength band while varying the center wavelength of the inspection light and / or imaging light at a predetermined pitch. By checking whether or not an image approximate to the representative image imaging wavelength and / or a predetermined wavelength range of the reference specimen material has been acquired, and / or the difference band of the similar image of each representative image at the required location Perform comparative discrimination.

  Here, the collation data will be described using the imaging log example of FIG. The imaging log is composed of a search specification part and an imaging data index part. The search number is a number assigned to each sample or each search unit. The sample size indicates the size of the medium to be imaged, and has a size of 50 mm × 50 mm in this example. The irradiation wavelength was 250 nm to 970 nm, indicating that the irradiation wavelength was changed at a 30 nm pitch. The camera indicates that the CCD camera is used out of the CCD camera and the IR camera. “CCD image size = 4 × 4 (256 × 256)” indicates that 4 pixels × 4 pixels are handled as one unit and is treated as an area of 256 pixels vertically and horizontally. The CCD exposure time is 30 mS. “CCD exposure time automatic setting = 0” indicates OFF, and the CCD detection wavelength includes the sweep start wavelength, end wavelength, and imaging wavelength pitch. In this example, since all are 0, all wavelengths (white light) are set to be used. Will be. Arbitrary characters can be entered in the MEMO column for later reference. “Number of images = 25” indicates the number of captured images calculated based on the setting contents such as the irradiation wavelength, and indicates that there are 25 captured images and there are 25 types with different measurement conditions. Next, it is shown that the cooling temperature of the CCD image sensor is −30 ° C. and the IR image sensor is not used. The cut-out position indicates coordinates within the effective area of the camera captured image, and is set to 10, 33, 29, 233. The white reference position indicates a white reference image area, and is a rectangular area indicated by 119, 39, 127, 47. The black reference image area is a rectangular area indicated by 123, 238, 131, and 246. Folder is the name of a folder in the hard disk that stores captured image data, and uses a search number.

  The index part of the latter half of the imaging data assigns serial numbers to each imaging from the start to the end of the search, and leaves the conditions for the imaging. For example, the line 00000003 is described as follows. 17:28:50 indicates the imaging time, indicating that imaging was performed at 17:28:50. F = MCX0250-0000. BMP means an image file in the BMP format, and real image data is stored with this file name. A CCD image pickup device is used as an image pickup means, a xenon lamp is used as a lamp, and irradiation light that is inspection light is used. The wavelength is 250 nm, which means that the imaging side transmits all wavelength light.

  The data following the file name indicates that T = 30.0 is the exposure time of 30.0 mS, and W = 636 indicates that the white reference read value at the white reference position under the above conditions is a 636AD value. B = 621 indicates that the black reference read value at the black reference position is the 621AD value. S = 735 >> 601 is an effective dynamic range value to be corrected. When corrected, a dynamic range of 256 gradations is taken between 735AD and 601AD values. OK at the end means a normal captured image.

  Here, as the verification data, the file name data shown in FIG. 30 such as the feature extraction conditions of the optical characteristics and the data of the attached imaging conditions described above are left and the actual image data is deleted, so that memory can be saved.

  The second method of paper sheet feature extraction and classification is a self-organizing feature map, which is a method of neural network using competitive learning, as part of image classification processing. Use as a mapping operation. This self-organizing feature map method is proposed by Kohonen as one of the neural network model paradigms. In the present invention, self-organization feature map is designed for competitive learning, which is a method of unsupervised learning to improve classification performance. Adapt organizational learning rules. The concept will be described below with reference to FIGS.

  First, a two-layer network as shown in FIG. 20 is assumed. The first layer is an input layer, and the second layer is a competitive layer. The competitive layer is a two-dimensional grid. Each input unit in the input layer is associated with all units in the competitive layer.

  Given an input pattern, an input layer unit takes the value of the corresponding element of the input pattern. The competitive layer adds the inputs and finds the only winner.

  In FIG. 20, each mutual connection has a weight value. In the initial state, a random weight value is given.

  FIG. 21 shows how a random input pattern is obtained. A random number generator gives a number to each element of the pattern vector. The numbers obtained from the random number generator are uniformly distributed between 0 and 1.

  The input pattern of Kohonen feature map is expressed as follows.

E = [e ₁ , e ₂ , e ₃ ,..., E _n ] (E is a captured image, n is the number of pixels)
FIG. 22 shows how each unit of this input pattern is combined with a specific unit in the competitive layer. The weight is U _i = [u _i1 , u _i2 ,..., U _in ] (U _i is a predicted feature image, n is the number of pixels)
Given in. i represents the unit of the competitive layer and is the number of the prediction feature image.

The Kohonen feature map first calculates a matching value for each unit in the competitive layer. This value is a measure for measuring the degree to which the weight of each unit matches the corresponding value of the input pattern. The match value for unit i is ‖E−U _i ‖
It becomes. This is the distance between the vectors E and U _i and is calculated by the following equation.
(J is the pixel number, i is the number of the predicted feature image)

The unit with the lowest match value (the best match) (predicted feature image) wins the competition. If the best matching unit is represented by c, c is ‖E−U _c ‖ = min {‖E−U _i ‖}
It is chosen as follows. The minimum value is selected from all the units i (predicted feature images) in the competitive layer. When there are a plurality of units (predicted feature images) having the same matching value, the unit having the smallest index value i (predicted feature image number) is selected.

Once the winner unit is determined, determine the vicinity of that unit. This is shown in FIG. A unit surrounding the winner unit c in a square is defined as a neighborhood. The neighborhood is represented by a set N _c of units. The size of the neighborhood changes.

The weights of all units near the winner unit c are adjusted. The adjustment equation is Δu _ij = α (e _j −u _ij ): when the unit i is in the neighborhood N _c Δu _ij = 0: otherwise. U _ij ^new = u _ij ^old + Δu _ij
It is.

  By this adjustment, a winner unit (predicted feature image) having a corrected weight and more approximate to the input pattern and its vicinity are obtained.

  The learning rate α of the adjustment equation has a relatively large initial value (2 to 0.5), but decreases as the exercise is repeated many times. The reduction rate is expressed by the following equation.

In the above equation, t is the current number of exercises, and T is the total number of exercises to be performed. The learning rate α starts from the initial value α ₀ and decreases until reaching the value 0.

The width of the neighborhood is also relatively large at the initial value and decreases with repeated training. The position of the winner unit c in FIG. 23 is (x _c , y _c ). If the distance from c to the neighboring edge is d, the neighborhood is c−d <x <c + d
And cd <y <c + d
It consists of all (x, y) that satisfy

The value of d decreases with training. The initial value d ₀ of d is set to 1/2 or 1/3 of the width of the competitive layer (the area of the initial predicted feature image). d is obtained by the following equation.

In the above equation, t is the current number of exercises, and T is the total number of exercises to be performed. d decreases linearly from d ₀ to 1.

  The above self-organizing feature map method is applied to image analysis as follows. First, a plurality of index data (predicted feature images) separately designated for the competitive layer is set. The index data (predicted feature image) is a vector set at random. In this case, the index data (predicted feature image) is created by shifting the average data of the image data (analyzed image) to be processed by a predetermined width. Gives the status as "feature image". A vector of the acquired image (analysis image) is input to the input layer.

  Each predicted feature image and the acquired captured image are sequentially compared, and the coincidence value is calculated as a geometric distance, that is, a value of the Euclidean distance. The predicted feature image with the lowest matching value (best matching, most approximate) is the winner. It is assumed that the acquired image has a similar relationship with the predicted feature image of the winner.

The weights of the winner and the predicted feature image in the vicinity thereof are corrected based on the adjustment equation described above. That is, the predicted feature image is corrected so as to be closer to the acquired image having the similar relationship. This is shown in FIG. In FIG. 24, u _{i (t)} represents a predicted feature image, and e _i represents an acquired image having a similar relationship, in the form of a vector. u _{i (t + 1)} represents the predicted feature image corrected based on the acquired image having the similar relationship, and is also represented in the form of a vector. When comparison (exercise) is performed once again, u _{i (t + 1)} and e _i are compared, and a predicted feature image u _{i (t + 2)} approaching e _i is generated. In this way, as the comparison (exercise) is repeated, the predicted feature image becomes closer to the acquired image.

By the way, the number of acquired images that are similar to the predicted feature image u _{i (t)} is not limited to one. In addition to neighboring images such as e _i-1 and e _{i + 1} , separated images e _{i + x} may have a similar relationship. Each time it is compared with such a similar image, the predicted feature image is subject to modification.

  In this way, the acquired image is sequentially compared with a plurality of predicted feature images and is assumed to have a similar relationship with the most similar predicted feature image, and the predicted feature image is further approximated to the captured image having the similar relationship. By repeating the process of correcting and sequentially comparing the captured image again with the corrected predicted feature image, the predicted feature image gradually converges to one point. At the end of the predetermined number of learnings, the comparison is aborted, and the corrected predicted feature image at that time is set as the final predicted feature image.

  In the first round of comparison, almost every predicted feature image has a similar relationship with any captured image. While the comparison is repeated many times and the value of the predicted feature image is modified and changed, there may be a conflict between the predicted feature images that have not been competed until now. If a conflict occurs, one will always be a winner and the other will be a loser (if the degree of approximation is the same, the index value i (the number of the predicted feature image) is the winner), so the captured images that have been of a similar relationship In some cases, the image is taken away by other predictive feature images. In the processing according to the present invention, all the predicted feature images that have been deprived of all similar captured images are no longer meaningful, and are eventually deleted.

  Further, in the present invention, when there are a plurality of predicted feature images within a predetermined degree of approximation, the predicted feature images are excessively integrated and updated to a single predicted feature image obtained by averaging their integrated values. The previous predicted feature image is deleted.

  Furthermore, in the present invention, the captured image normally has a similar relationship with any one of the predicted feature images, but some captured images do not have a similar relationship with any predicted feature image at a predetermined distance. Therefore, when a captured image that is not within the predetermined approximate range with any of the predicted feature images and does not have a similar relationship within a separately determined dispersion tolerance value, a new predicted feature image is created using these captured images. Create

  This series of image analysis is performed according to the flowchart of FIG.

  First, in step S201, initial index data (predicted feature image) is created. Here, initial index data (predicted feature image) is obtained by adding a small random number to each elemental average value of a plurality of captured images (usually 20 to 200 images) to be classified. The initial index data (predicted feature images) is created separately (usually 9 to 16) as designated predictive feature images. The average value for each element is obtained from the data of all acquired images, but may be obtained from the data of arbitrarily selected captured images.

In step S202, a calculation constant for classifying all the captured image data into the same category is set for each of the initial index data (predicted feature images) as an initial constant of the mapping calculation. T indicates the number of learning times, and is normally set to 1000 times. α ₀ indicates an initial learning rate, and is usually set to 0.5. d ₀ indicates an initial neighborhood width, and is usually set to 1/3 or 1/4 of the width of the aforementioned competitive layer (initial predicted feature image).

  In steps S203 and S204, a mapping calculation is performed for each of the initial index data (predicted feature images) using the calculation constant. Details are as described in the self-organizing feature map method described above.

  In step S205, the Euclidean distance between the index data (predicted feature image) and each of the captured images corresponding to the same category is calculated for each index data (predicted feature image) that has been subjected to the similar classification operation.

  In step S206, it is determined whether the Euclidean distance between the index data (predicted feature image) and each captured image corresponding to the index data is within a predetermined approximate range or out of the approximate range. If it is out of the approximate range, the process proceeds to step S207. .

  In step S207, the average value image of the captured images outside the allowable value is added as sub-index data (predicted feature image) of the index data (predicted feature image), and these index data (predicted feature image) and sub-index data (predicted). The mapping operation from step S202 is executed again on the captured image corresponding to the same type of feature image. The mapping operation is executed only in the neighborhood width of 1 fixed value.

  According to the above, in the case where there is a captured image with a low degree of similarity in which the Euclidean distance is outside the approximate range for any index data (predicted feature image), sub-index data (predicted feature image) is matched to the captured image. The captured image that has been additionally set and already classified in the index data (predicted feature image) is also reclassified to the plurality of index data (predicted feature image) including the sub-index data (predicted feature image). Is.

  On the other hand, if it is determined in step S206 that the Euclidean distance between all captured images and the index data (predicted feature image) corresponding to the same is within the approximate range, the process proceeds to step S208.

  In step S208, the Euclidean distance between all index data (predicted feature images) is calculated to obtain a pair of index data (predicted feature images) at the shortest distance. Furthermore, the Euclidean distance between the captured images corresponding to the same kind of the index data (predicted feature image) forming a pair is calculated, and the maximum one is obtained.

  After the maximum Euclidean distance between captured images corresponding to the same kind of index data (predicted feature image) at the shortest distance is obtained in step S208, it is determined in step S209 whether the maximum Euclidean distance is within a predetermined determination value. . If it is within the determination value, the process proceeds to step S210.

  In step S210, the average value of both index data (predicted feature images) at the shortest distance is set as new index data (predicted feature images), and the original both index data (predicted feature images) are deleted. Then, the calculation from step S208 is executed again.

  According to the above, when an image approximating a predetermined approximate value or more is excessively classified into a plurality of index data (predicted feature images), the plurality of index data (predicted feature images) is an appropriate new index. The data (predicted feature image) is integrated and updated.

  On the other hand, if it is determined in step S209 that the maximum Euclidean distance is outside the determination value, the process proceeds to step S211.

  In step S211, a search is made as to which captured image corresponds to each index data (predicted feature image). If it is determined in step S212 that there is non-corresponding index data (predicted feature image) that does not correspond to any captured image in the same manner, all of the non-corresponding index data (predicted feature image) is determined in step S213. Deleted. On the other hand, if there is no data determined as non-corresponding index data (predicted feature image) in step S212, a series of processing ends with a conclusion that only valid index data (predicted feature image) exists.

  Each captured image to be analyzed as described above is classified into index data (predicted feature image) within an approximate range and index data (predicted feature image) groups that are distributed more than a predetermined degree of approximation without excess or deficiency. It will be sorted. In addition, for storing these processing results, each predicted feature image as a representative image, which is the detailed image data obtained by the feature extraction calculation, and collation data of captured images classified into the same category are stored. . Although the predicted feature image includes an image as it is captured, it may be processed and compressed data. Therefore, the feature extraction apparatus 1 has a minimum Euclidean distance from each predicted feature image, although not shown. The camera image data of the captured image is also stored and saved as a representative real image.

  In other words, the predicted feature image is a representative image having an average feature extracted and classified from each captured image with a predetermined calculation accuracy. Detailed camera image data corresponding to this representative image is representative. It becomes an image. For this reason, even if high-speed processing is simply performed on the basis of compressed image data that is separately set with optional classification, detailed camera image data is retained as a representative real image as it is. When the calculation is to be performed, it is possible to perform feature extraction with high accuracy using the quantity information of the sorted images obtained from the respective representative real image data and the collation data.

  Further, in the above classification sorting calculation method, it is necessary that all captured images to be classified exist at the start of calculation. Therefore, in order to reduce the calculation load, a large amount of image data is divided into a predetermined number (for example, 20 to 200 images) and subjected to calculation processing (hereinafter referred to as “division calculation processing”), and all division calculation processing is performed. After completion of the above, similar sort processing is further performed in the same manner as described above for each feature image obtained by the division calculation processing. In the similar sort process, the predicted feature image obtained by the previous split calculation process or representative real image data corresponding to each of the predicted feature images is selectively used. Finally, the characteristics of all the image data are extracted based on image data with compression accuracy that is arbitrarily selected separately.

  As described above, several comparisons (learning) are repeated to determine a plurality of predicted feature images and converge each value. This clarifies the characteristics of the sample. When performing feature extraction of another sample, the necessary number is checked to determine whether each wavelength band image captured from another sample has a similar relationship with these predicted feature images.

  26 to 28 show examples in which image groups are classified into similar categories. FIG. 26 shows a total of 13 images obtained by imaging actual samples at different wavelengths. The captured wavelengths are as shown in FIGS. As a result of the calculation, it was first classified into 6 groups as A to F as shown in FIG. 27. Next, when the brightness of one point of the image was shift-corrected to the same level value and the calculation was performed again, This time, as shown in FIG. 28, the groups were classified into four groups A to D as in the case of visual feature extraction.

  Here, if a reference point of brightness is provided in the acquired image and image correction is performed to match the brightness level values of the light and dark reference points of each image, it is possible to understand the feature almost as much as human visual feature confirmation. Similar classification is possible.

  There is also a method that does not use all pixel data to determine the characteristics of a sample from image data. An example of the method is shown in FIG. Here, first, the image is binarized. Then, the number of black image (or white image) pixels in each row and column of the pixel matrix is examined, and the number data of each row and column is used as a feature. Instead of binarization, the data amount of each pixel may be weighted as a gray scale in units of rows and columns, and the feature pattern may be obtained by the addition value or the average value of each row and column. Alternatively, a predetermined number of blocks of all pixels may be used, and a compressed image obtained by taking the average value of the blocks may be used.

  In obtaining a representative image, as described above, the first method includes a sequential comparison calculation method, and the second method applies a self-organizing feature map method. It may be selected and used, or only one of them may be implemented.

  In the above description, the entire image on the paper surface of the sample is targeted. However, the same object can be achieved with the same configuration even when the captured image has optical characteristics for each inspection wavelength light on the limited region surface instead of the entire paper surface.

  Each embodiment of the present invention has been described above, but various modifications can be made without departing from the spirit of the present invention.

  The present invention can be widely used in a feature extraction method for optically analyzing the surface of a sample.

The block diagram of the feature extraction apparatus for performing the feature extraction method of the present invention, with the optical mechanism portion being a sectional view Horizontal section of the feature extraction unit A horizontal sectional view similar to FIG. 2, showing different states Horizontal section of the light source A horizontal sectional view similar to FIG. 4 showing different states Front view of bandpass filter Block diagram of feature extraction device The figure which shows the change of the picture when it picks up while shifting the wavelength A diagram conceptually showing the situation where images taken by multiple cameras are used without correction The figure which shows ideally the situation of using the images captured by multiple cameras with correction The figure which shows the situation where the light and dark reference point for camera correction is set in the sample image Illustration of light and dark reference plate for camera correction A diagram illustrating the first feature extraction method and showing the difference image A table of AD values expressing the difference value of an image as a digital value Table of exponents that are absolute values of difference values Index graph 1st explanatory drawing of the method of selecting a representative image based on a difference value 2nd explanatory drawing of the method of selecting a representative image based on a difference value Flow chart of image classification work First explanatory diagram of the principle of operation in a diagram explaining the second feature extraction method Second explanatory diagram of the above operating principle Third explanatory diagram of the above operating principle Fourth explanatory diagram of the above operating principle Diagram for explaining the application of the above operating principle to image analysis Flow chart of image classification work Diagram of an example image to which the second feature extraction method is applied The 1st table | surface which shows the classification exercise result of the example image of FIG. The 2nd table which shows the classification practice result of the example image of FIG. The figure explaining the 3rd feature extraction method Diagram explaining imaging log example

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Feature extraction apparatus 2 Main body part 3 Arithmetic apparatus 10 Housing 11 Optical section 12 Control section 23 Sample holder 30 Inspection light generator 31 Light source part 38 Spectroscope 50 Imaging apparatus 51 CCD camera 52 Infrared camera 57 Spectroscope 58 Band pass filter 87 Image Analysis part

Claims (4)

The sample is selectively irradiated with light in the wavelength range from the ultraviolet region to the near-infrared region, and all the wavelength region light or multiple wavelength band light having different center wavelengths as inspection light, and each of the irradiated inspection lights In contrast, a method of obtaining a plurality of captured images by sequentially capturing light from the sample for each of predetermined wavelength bands having different center wavelengths, and extracting optical characteristics of the sample from these captured images, ,
A first step of setting a plurality of predicted feature images as index data for the similar classification process;
A second step of sequentially correcting each of the plurality of captured images so as to approach the captured image by assuming that the most similar predicted feature image has a similar relationship while comparing the degree of approximation with the plurality of predicted feature images; ,
A third step of gradually converging each feature image as a representative image of a similar captured image by making the correction of the predicted feature image to the similar captured image smaller than the previous step and repeatedly performing the second step; ,
A feature extraction method characterized by comprising:   When there is a captured image that is not included in a predetermined approximate range for any of the predicted feature images converged among the plurality of captured images, a new predicted feature image is created using these captured images The feature extraction method according to claim 1, wherein:   The feature extraction method according to claim 1, wherein when the predicted feature image that is not similar to any of the plurality of captured images is generated, the predicted feature image is deleted.   When the distance between the converged predicted feature images is within a predetermined value and the maximum distance between a plurality of captured images corresponding to the same type of the predicted feature image is within a separately set value, these predictions The feature extraction method according to claim 1, wherein the feature image is integrated and updated to these average values.