Determination device, determination method, and determination program

Abstract

To provide a determination device capable of determining color of a determination object with higher robustness as compared with a case where evaluation is made with a simple statistical index.SOLUTION: There is provided a determination device 10 which: photographs, with a photographing device 200, a color sample being a reference of color and a determination object; performs sampling to each photographed image by a bootstrap method; respectively generates a first feature quantity pool and a second feature quantity pool comprising M-kinds of feature quantities by converting the sampling result to M-kinds (M is a natural number) of color spaces; obtains amounts of spatial variations from the M-kinds of feature quantities of the first feature quantity pool; obtains K pieces of feature quantity differences by calculating difference between each of the first feature quantity pool and the second feature quantity pool; and performs ensemble learning for the feature quantity difference with a categorical variable corresponding to the determination result of the determination object as an objective variable, and with the amounts of spatial variations as a loss function.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a determination device, a determination method, and a determination program. [Background technology]

[0002] There are techniques for determining whether the color of a manufactured product matches a predetermined color sample. For example, Patent Document 1 discloses a technique for determining the color by quantifying the color of a two-dimensional printed matter or a three-dimensional solid object using the average value and frequency of brightness and hue. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-188790 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, due to the influence of texture or warping, the apparent color of the object to be judged (object to be judged) may differ from the original color. Conventionally, evaluation has been performed using simple statistical indices (average value, mode, area ratio) as in the technology disclosed in Patent Document 1, but evaluation using simple statistical indices has low robustness.

[0005] The present invention has been made in consideration of the above points, and aims to provide a judgment device, a judgment method, and a judgment program that are capable of judging the color of an object to be judged with high robustness compared to evaluation using simple statistical indicators. [Means for solving the problem]

[0006] A determination device according to a first aspect of the present invention includes a sampling unit that performs sampling by a bootstrap method on first image data in which a color sample serving as a color reference is captured, and second image data in which an object to be determined is captured; a feature generation unit that performs conversion of the sampling results of the first image data and the second image data into M types of color spaces (M is a natural number) to generate a first feature pool and a second feature pool each consisting of M types of features; a spatial variation calculation unit that obtains a spatial variation by calculating a standard deviation for the M types of features in the first feature pool; a difference acquisition unit that obtains K difference features by taking differences between the features of the first feature pool and the second feature pool using K types (K is a natural number) of distance calculation methods; and a learning unit that performs ensemble learning for the K difference features using a categorical variable corresponding to the determination result of the object to be determined as a target variable and the spatial variation as a loss function.

[0007] According to the first aspect of the present invention, by using differential feature amounts and spatial variation amounts calculated based on feature amounts obtained from color swatches and samples, it is possible to determine the color of an object to be determined with high robustness compared to evaluation using simple statistical indicators.

[0008] A determination device according to a second aspect of the present invention is the determination device according to the first aspect, wherein the feature amount is a value representing a color space after conversion of the first image data and the second image data.

[0009] According to the second aspect of the present invention, the difference feature amount and the spatial variation amount can be obtained using the value representing the color space after conversion.

[0010] A determination device according to a third aspect of the present invention is the determination device according to the first or second aspect, wherein the spatial variation calculation unit multiplies the standard deviation calculated for each type of feature by a predetermined weight and adds the multiplied values ​​together to obtain the spatial variation.

[0011] According to the third aspect of the present invention, it is possible to quantitatively evaluate the degree of variation in feature amounts after weighting the types of feature amounts.

[0012] A determination method according to a fourth aspect of the present invention includes a process executed by a computer to perform sampling using a bootstrap method on first image data in which a color sample serving as a color reference is captured, and second image data in which an object to be determined is captured, converting the sampling results of the first image data and the second image data into M types of color spaces (M is a natural number) to generate a first feature pool and a second feature pool each consisting of M types of features, calculating a standard deviation for the M types of features in the first feature pool to obtain a spatial variation, taking differences between the features of the first feature pool and the second feature pool using K types of distance calculation methods (K is a natural number) to obtain K difference features, and performing ensemble learning using a categorical variable corresponding to the determination result of the object to be determined for the K difference features as a target variable and the spatial variation as a loss function.

[0013] According to the fourth aspect of the present invention, by using a differential feature amount and a spatial variation amount calculated based on feature amounts obtained from a color swatch and a sample, it is possible to determine the color of an object to be determined with high robustness compared to evaluation using a simple statistical index.

[0014] A judgment program according to a fifth aspect of the present invention causes a computer to execute the following processes: sampling, by a bootstrap method, first image data in which a color sample serving as a color reference is captured, and second image data in which an object to be judged is captured; converting the sampling results of the first image data and the second image data into M types of color spaces (M is a natural number) to generate a first feature pool and a second feature pool each consisting of M types of features; obtaining a spatial variation by calculating a standard deviation for the M types of features in the first feature pool; taking differences between the features of the first feature pool and the second feature pool using K types of distance calculation methods (K is a natural number) to obtain K difference features; and performing ensemble learning for the K difference features using a categorical variable corresponding to the judgment result of the object to be judged as a target variable and the spatial variation as a loss function.

[0015] According to the fifth aspect of the present invention, by using a differential feature amount and a spatial variation amount calculated based on feature amounts obtained from a color swatch and a sample, it is possible to determine the color of an object to be determined with high robustness compared to the case of evaluation using a simple statistical index. Effect of the Invention

[0016] According to the present invention, by creating robust judgment criteria from image data, it is possible to provide a judgment device, judgment method, and judgment program that are capable of judging the color of an object to be judged with high robustness compared to evaluation using simple statistical indicators. [Brief description of the drawings]

[0017] [Figure 1] 1 is a diagram showing a schematic configuration of a determination system including a determination device according to an embodiment of the present invention; [Diagram 2] FIG. 2 is a block diagram showing a hardware configuration of the determination device. [Diagram 3] FIG. 2 is a block diagram showing an example of a functional configuration of a determination device. [Figure 4]FIG. 13 is a diagram showing an example of sampling by a bootstrap method in a sampling unit. [Diagram 5] 13A and 13B are diagrams illustrating examples of histograms obtained by hue conversion performed by a feature generating unit. [Figure 6] FIG. 13 is a diagram illustrating the amount of spatial variation. [Figure 7] 11 is a diagram illustrating an example of a method for calculating a difference feature amount by a difference acquisition unit. [Figure 8] FIG. 1 is a diagram illustrating a GBDT used by a determination device. [Figure 9] 4 is a flowchart showing a flow of a determination process performed by the determination device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, an example of an embodiment of the present invention will be described with reference to the drawings. In each drawing, the same or equivalent components and parts are given the same reference numerals. In addition, the dimensional ratios of the drawings are exaggerated for the convenience of explanation and may differ from the actual ratios.

[0019] Fig. 1 is a diagram showing the schematic configuration of a determination system equipped with a determination device according to this embodiment. Shown in Fig. 1 is the schematic configuration of a determination system that compares the color of a manufactured sample with a reference color and outputs a result of determining the color of the sample.

[0020] The determination system 1 shown in FIG.

[0021] The determination device 10 is a device that uses images of the color sample 210 and the sample 211 captured by the imaging device 200 to output a determination result for the color of the sample 211. The imaging device 200 is fixed to a tripod (not shown) or the like, and captures images of the color sample 210 and the sample 211 placed on the imaging stand 230. The mounting surface 231 of the imaging stand 230 is at an angle of 45 degrees from the horizontal. In this embodiment, the color sample 210 and the sample 211 are captured in a darkroom, and a light source 220 is installed in the darkroom. In this embodiment, the distance between the light source 220 and the bottom side of the imaging stand 230 is 765 mm, and the distance between the imaging device 200 and the color sample 210 and the sample 211 is 445 mm. The imaging device 200 captures images of the color sample 210 and the sample 211 by setting the shutter speed to 1 / 15 seconds, the aperture to f8.0, and the ISO sensitivity to 800.

[0022] When light from the light source 220 is reflected by the sample 211, the apparent color of the sample 211 to be determined may differ from the original color due to the influence of grain or bending. The determination device 10 according to this embodiment is a device that makes it possible to determine the color of the sample 211 with high robustness compared to evaluation using a simple statistical index.

[0023] Specifically, the determination device 10 according to this embodiment performs sampling from one image using the bootstrap method, and acquires multiple feature amounts from one sampling result. Then, the determination device 10 analyzes the content of the multiple feature amounts, and performs a learning process to determine whether the color of the sample 211 matches the color of the color sample 210. The determination device 10 according to this embodiment creates a robust determination criterion from the image data of the color sample 210 and the sample 211, and can determine the color of the object to be determined with high robustness compared to evaluation using a simple statistical index.

[0024] FIG. 2 is a block diagram showing a hardware configuration of the determination device 10. As shown in FIG.

[0025] 2, the determination device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to each other via a bus 19 so as to be able to communicate with each other.

[0026] The CPU 11 is a central processing unit, and executes various programs and controls each part. That is, the CPU 11 reads a program from the ROM 12 or the storage 14, and executes the program using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various arithmetic processing according to the program recorded in the ROM 12 or the storage 14. In this embodiment, the ROM 12 or the storage 14 stores a determination program for determining the color of the sample 211 using an image captured by the imaging device 200.

[0027] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores programs or data as a working area. The storage 14 is configured with a storage device such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory, and stores various programs including an operating system, and various data.

[0028] The input unit 15 includes a pointing device such as a mouse, and a keyboard, and is used to perform various input operations.

[0029] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may function as the input unit 15 by adopting a touch panel system.

[0030] The communication interface 17 is an interface for communicating with other devices such as the imaging device 200, and uses standards such as Ethernet (registered trademark), FDDI, and Wi-Fi (registered trademark).

[0031] When executing the above-mentioned determination program, the determination device 10 realizes various functions using the above-mentioned hardware resources. The functional configuration realized by the determination device 10 will be described.

[0032] FIG. 3 is a block diagram showing an example of a functional configuration of the determination device 10. As shown in FIG.

[0033] 3, the determination device 10 has, as functional components, a sampling unit 101, a feature generating unit 102, a spatial variation calculating unit 105, a difference acquiring unit 106, a learning unit 107, and a determination unit 108. Each functional component is realized by the CPU 11 reading out and executing a determination program stored in the ROM 12 or the storage 14.

[0034] The sampling unit 101 samples image data of the color sample 210 and image data of the sample 211 captured by the imaging device 200. The image of the color sample 210 is an example of the first image data of the present invention, and in this embodiment, the sampling unit 101 samples N sets (N is a natural number) of images of the color sample 210 and the sample 211 by the bootstrap method. The bootstrap method is a method of randomly obtaining many samples from one specimen, allowing overlaps. The number of sets N of sampling by the bootstrap method in the sampling unit 101 may be determined by the user. A user interface for inputting the number of sampling sets N may be displayed on the display unit 16.

[0035] 4 is a diagram showing an example of sampling by the bootstrap method in the sampling unit 101. In this embodiment, the sampling unit 101 randomly extracts sub-regions 320 from the image data 310 of the color sample 210 and the image data 311 of the sample 211, allowing overlap. In this embodiment, about 200 sub-regions 320 (i.e., N=200) are extracted from each image data. Note that the size of the sub-regions 320 is not limited to a specific size.

[0036] The feature generation unit 102 converts the image data of the color sample 210 sampled by the sampling unit 101 and the image data of the sample 211 into M types of color spaces (M is a natural number). For the image data of the color sample 210, the feature generation unit 102 generates a first feature pool 103 consisting of M types of feature amounts, and for the image data of the sample 211, generates a second feature pool 104 consisting of M types of feature amounts.

[0037] Which feature quantity can be used for the most robust evaluation varies depending on the situation when the color sample 210 and the sample 211 are captured, and therefore it is difficult to determine a specific feature quantity. Therefore, the feature quantity generating unit 102 converts all possible feature quantities and pools the information on the feature quantities. In this embodiment, the feature quantity generating unit 102 obtains feature quantities for each image data by performing hue conversion such as L*a*b* conversion, YCrCb conversion, Luv conversion, hls conversion, hsv conversion, and xyz conversion. Note that the type of conversion to be performed on each image data may be specified by the user of the determination device 10.

[0038] FIG. 5 is a diagram showing an example of a histogram obtained by the hue conversion by the feature generating unit 102. In FIG. 5, as an example, the result of performing the hue conversion to the L*a*b* color space on two samples is shown in a histogram. By the hue conversion to the L*a*b* color space, a feature representing brightness, a feature representing red and green, and a feature representing yellow and blue are obtained. By looking at the feature represented by the histogram and the reference (ref) feature, the evaluator decides which feature should be adopted to enable accurate judgment. That is, by adopting a feature having a histogram that deviates from the histogram of the reference feature, it becomes possible to accurately judge the color of the sample 211 using the color sample 210.

[0039] 5, the NG histogram of a* for sample 1 deviates from the shape of the histogram of the reference feature. Therefore, by adopting a* as the feature for sample 1, it becomes possible to accurately determine the color of sample 211 using color sample 210.

[0040] The spatial variation calculation unit 105 calculates the spatial variation from the first feature pool 103 generated by the feature generation unit 102. That is, the spatial variation calculation unit 105 calculates the spatial variation based on the sampling result of the color sample 210. In this embodiment, the spatial variation refers to an amount indicating the degree to which the feature varies. In this embodiment, the spatial variation calculation unit 105 obtains the spatial variation by calculating the standard deviation of the feature accumulated in the first feature pool 103.

[0041] The spatial variation calculation unit 105 may take as the spatial variation a value obtained by multiplying the standard deviations calculated for each type of feature by a predetermined weight and adding the results together. By taking as the spatial variation a value obtained by multiplying the standard deviations calculated for each type of feature by a predetermined weight and adding the results together, it is possible to quantitatively evaluate the degree of variation in the feature after weighting the type of feature.

[0042] FIG. 6 is a diagram for explaining the spatial variation amount using a histogram. A wide width of each feature amount shown in the histogram in FIG. 6 means a large standard deviation. In other words, a large standard deviation means a large spatial variation. And a large spatial variation means that it is not robust. On the other hand, a narrow width of a feature amount means a small standard deviation. A small standard deviation means a small spatial variation. A small spatial variation means that it is robust. Therefore, by the spatial variation amount calculation unit 105 calculating the spatial variation amount, it is possible to find a robust index. In other words, by the spatial variation amount calculation unit 105 calculating the spatial variation amount, it is possible to find a feature amount that has a sharp shape when it is made into a histogram.

[0043] For example, if a sub-region is 100 pixels long and 100 pixels wide, and RGB values ​​are input to each pixel, each of the three feature quantities R, G, and B will have 10,000 data points. The spatial variation calculation unit 105 calculates the standard deviation for these 10,000 pieces of data, thereby obtaining three standard deviation values ​​for one image.

[0044] The difference acquiring unit 106 calculates the difference between the features stored in the first feature pool 103 and the second feature pool 104 for each type of feature to obtain differential features. In this embodiment, the difference acquiring unit 106 uses K types (K is a natural number) of distance calculation methods to obtain the differences between the features in the first feature pool 103 and the second feature pool 104 to obtain K differential features.

[0045] It is difficult to determine a specific distance calculation method because the most robust evaluation can be performed using a distance calculation method that depends on the situation when the color sample 210 and the sample 211 are captured. Therefore, the difference acquisition unit 106 calculates the difference using as many known distance calculation methods as possible. Examples of distance calculation methods include Euclidean distance, standardized Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, Canberra distance, Bray-Curtis distance, Haversine distance, Mahalanobis distance, Minkowski distance, cosine distance, interlayer distance, Hamming distance, Jaccard coefficient, Dice coefficient, Russel-Rao coefficient, Rogers-Tanimoto coefficient, sokalmichener, sokalsneath, yule, etc. The distance calculation method to be used for each feature pool may be specified by the user.

[0046] The difference acquiring unit 106 calculates the histogram difference for each of the M feature amounts by applying K types of distance calculation methods. Therefore, the difference acquiring unit 106 creates M×K difference feature amounts from one set. Therefore, the difference acquiring unit 106 can obtain a difference feature amount matrix of N rows and M×K columns.

[0047] FIG. 7 is a diagram showing an example of a method for calculating a difference feature by the difference acquisition unit 106. FIG. 7 shows an example of calculating the Euclidean distance between the feature of the color sample 210 stored in the first feature pool 103 and the feature of the sample 211 stored in the second feature pool 104. The Euclidean distance is the square root of the sum of the squares of the difference in the properties of the data. By calculating the Euclidean distance over the entire spectrum, it is possible to grasp not only the difference between the peaks of the two spectra but also the difference in the shape of the spectral distribution. The difference acquisition unit 106 calculates the Euclidean distance between the feature of the color sample 210 and the feature of the sample 211 at each point. That is, the greater the difference between the feature of the color sample 210 and the feature of the sample 211, the greater the Euclidean distance.

[0048] The learning unit 107 learns the learning model 20 for outputting the judgment result of the sample 211 by machine learning. There are many machine learning algorithms that automatically classify data, but in this embodiment, a method called GBDT (Gradient Boosting Decision Tree) is used. The reason for using GBDT is that the judgment criteria can be flexibly changed since the data has characteristics in which the judgment criteria change for each sample.

[0049] Fig. 8 is a diagram explaining the GBDT used by the determination device 10. The determination device 10 determines whether the color of the sample 211 matches the color of the color sample 210 by majority vote of a large number of discriminators. Fig. 8 shows an example in which it is determined whether the color of the sample 211 matches the color of the color sample 210 by majority vote of the discrimination results by discriminators using two indexes. Differential feature amounts calculated by different distance calculation methods are used for index 1 and index 2.

[0050] The learning unit 107 performs ensemble learning using a categorical variable (binary values ​​of OK and NG) corresponding to the judgment result of the sample 211 for the N-row, M×K-column differential feature matrix as a response variable and the spatial variation calculated by the spatial variation calculation unit 105 as a loss function. In the ensemble learning, learning is performed so that the estimation error of OK / NG is minimized using the categorical variable as a response variable. Then, the learning unit 107 sets the spatial variation as a loss function for the ensemble learning.

[0051] In this embodiment, the learning unit 107 performs ensemble learning using a feature that minimizes the spatial variation amount and a differential feature amount calculated by a distance calculation method that maximizes the differential feature amount. In the example of FIG. 8, differential feature amounts calculated by different distance calculation methods are used for index 1 and index 2, and the spatial variation amount is used as a criterion for determining whether the index is appropriate. The determination device 10 can improve the learning accuracy of the ensemble learning by setting the spatial variation amount in the loss function of the ensemble learning.

[0052] The determination unit 108 uses the results of ensemble learning by the learning unit 107 to determine whether the color of the sample 211 matches the color of the color sample 210. For example, the determination unit 108 outputs OK as the determination result if the color of the sample 211 matches the color of the color sample 210, and outputs NG as the determination result if the color of the sample 211 does not match the color of the color sample 210. The determination unit 108 may display the determination result on the display unit 16.

[0053] Next, the operation of the determination device 10 will be described.

[0054] 9 is a flowchart showing the flow of the determination process by the determination device 10. The CPU 11 reads out a determination program from the ROM 12 or the storage 14, loads it into the RAM 13, and executes it to perform the determination process.

[0055] In step S101, the CPU 11 samples image data of the color sample 210 and image data of the sample 211 captured by the imaging device 200. In this embodiment, the CPU 11 samples N sets of images of the color sample 210 and images of the sample 211 by the bootstrap method. In this embodiment, the CPU 11 samples approximately 200 sets of images of the color sample 210 and images of the sample 211 by the bootstrap method.

[0056] After sampling the image data of the color sample 210 and the image data of the sample 211 in step S101, the CPU 11 then generates a feature pool from the sampling results in step S102. The CPU 11 converts the image data of the color sample 210 and the image data of the sample 211 into M types of color spaces. The CPU 11 generates a first feature pool 103 consisting of M types of feature amounts for the image data of the color sample 210, and generates a second feature pool 104 consisting of M types of feature amounts for the image data of the sample 211. In this embodiment, the CPU 11 obtains the feature amounts for each image data by performing hue conversion such as L*a*b* conversion, YCrCb conversion, Luv conversion, hls conversion, hsv conversion, and xyz conversion.

[0057] Next, in step S103, the CPU 11 calculates a spatial variation amount from the first feature amount pool 103 obtained from the image data of the color sample 210. The spatial variation amount is an amount indicating the degree to which the feature amount varies, and in this embodiment, the CPU 11 obtains the spatial variation amount by calculating a standard deviation for the feature amounts accumulated in the first feature amount pool 103.

[0058] Next, in step S104, the CPU 11 calculates the difference between the features stored in the first feature pool 103 and the second feature pool 104 for each type of feature to obtain differential features. In this embodiment, the CPU 11 uses K types (K is a natural number) of distance calculation methods to calculate the differences between the features in the first feature pool 103 and the second feature pool 104 to obtain K differential features. Note that the CPU 11 may switch the order of the processing between step S103 and step S104, or may execute the processing of step S103 and step S104 in parallel.

[0059] Next, in step S105, the CPU 11 performs machine learning of the learning model 20 for outputting a judgment result of the sample 211. There are many machine learning algorithms that automatically classify data, but in this embodiment, the CPU 11 performs machine learning of the learning model 20 for outputting a judgment result of the sample 211 using GBDT.

[0060] Next, in step S106, the CPU 11 uses the learning model 20 learned by machine learning to output a judgment result of the sample 211. For example, if the color of the sample 211 matches the color of the color sample 210, the CPU 11 outputs OK as the judgment result, and if the color of the sample 211 does not match the color of the color sample 210, the CPU 11 outputs NG as the judgment result. The CPU 11 may display the judgment result on the display unit 16.

[0061] The determination device 10 can create robust determination criteria from image data by executing a series of processes. By creating robust determination criteria from image data, the determination device 10 can determine the color of an object to be determined with high robustness compared to evaluation using simple statistical indicators.

[0062] The effects of the determination device 10 according to this embodiment will be described. Table 1 shows the evaluation results of the determination accuracy of the sample 211 during cross-validation depending on whether or not sampling is performed using the bootstrap method and whether or not the amount of spatial variation is calculated.

[0063] [Table 1]

[0064] As shown in Table 1, when neither bootstrap sampling nor calculation of spatial variation is performed, the judgment accuracy is roughly half, which is almost the same as when OK or NG is selected randomly. When bootstrap sampling is not performed and only spatial variation is calculated, the judgment accuracy improves to 64%, but the calculation still outputs an incorrect judgment result about once in three times. When bootstrap sampling is performed and spatial variation is not calculated, the judgment accuracy improves to 85%. Furthermore, when bootstrap sampling is performed and spatial variation is calculated, the judgment accuracy improves further to 92%.

[0065] Therefore, the determination device 10 according to this embodiment performs sampling by the bootstrap method and calculates the amount of spatial variation, so that it is possible to output a correct determination result with a probability of 9 times out of 10 or more.

[0066] In addition, the determination process executed by the CPU by reading the software (program) in each of the above embodiments may be executed by various processors other than the CPU. In this case, examples of the processor include a PLD (Programmable Logic Device) such as an FPGA (Field-Programmable Gate Array) whose circuit configuration can be changed after manufacture, and a dedicated electric circuit such as an ASIC (Application Specific Integrated Circuit) which is a processor having a circuit configuration designed exclusively for executing a specific process. In addition, the determination process may be executed by one of these various processors, or may be executed by a combination of two or more processors of the same or different types (for example, a plurality of FPGAs, a combination of a CPU and an FPGA, etc.). In addition, the hardware structure of these various processors is, more specifically, an electric circuit that combines circuit elements such as semiconductor elements.

[0067] In addition, in each of the above embodiments, the program for the determination process is prestored (installed) in a ROM or storage, but the present invention is not limited to this. The program may be provided in a form recorded on a non-transitory recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The program may also be downloaded from an external device via a network. [Explanation of symbols]

[0068] 10 Judgment device 200 Imaging device 210 Color Samples 211 Sample 230 light source

Claims

1. a sampling unit that performs sampling by a bootstrap method on each of first image data in which a color sample serving as a color reference is imaged and second image data in which an object to be determined is imaged; a feature generating unit that converts sampling results of the first image data and the second image data into M types of color spaces (M is a natural number) to generate a first feature pool and a second feature pool each including M types of feature amounts; a spatial variation calculation unit that calculates a standard deviation for the M types of feature amounts in the first feature amount pool to obtain a spatial variation amount; a difference acquisition unit that acquires K difference features by calculating differences between the features in the first feature pool and the second feature pool using K types (K is a natural number) of distance calculation methods; a learning unit that performs ensemble learning using a categorical variable corresponding to a determination result of the object to be determined for the K difference feature amounts as a response variable and the spatial variation amount as a loss function; A determination device comprising:

2. The determination device according to claim 1 , wherein the feature amount is a value that represents a color space after conversion of the first image data and the second image data.

3. 3 . The determination device according to claim 1 , wherein the spatial variation calculation unit multiplies the standard deviation calculated for each type of the feature amount by a predetermined weight and adds the multiplied values ​​together to obtain the spatial variation.

4. Sampling the first image data in which a color sample serving as a color reference is imaged and the second image data in which the object to be determined is imaged by using a bootstrap method; converting the sampling results of the first image data and the second image data into M types of color spaces (M is a natural number) to generate a first feature pool and a second feature pool each consisting of M types of feature amounts; calculating a standard deviation for the M types of features in the first feature pool to obtain a spatial variation amount; calculating differences between the features in the first feature pool and the second feature pool using K types of distance calculation methods (K is a natural number), to obtain K difference features; A determination method, comprising: a process of performing ensemble learning for the K difference feature amounts, the categorical variable corresponding to the determination result of the object to be determined being used as a response variable, and the spatial variation amount being used as a loss function, the process being performed by a computer.

5. On the computer, Sampling the first image data in which a color sample serving as a color reference is imaged and the second image data in which the object to be determined is imaged by using a bootstrap method; converting the sampling results of the first image data and the second image data into M types of color spaces (M is a natural number) to generate a first feature pool and a second feature pool each consisting of M types of feature amounts; calculating a standard deviation for the M types of features in the first feature pool to obtain a spatial variation amount; calculating differences between the features in the first feature pool and the second feature pool using K types of distance calculation methods (K is a natural number), to obtain K difference features; a categorical variable corresponding to a judgment result of the object to be judged for the K difference features is used as a target variable, and the spatial variation amount is used as a loss function to perform ensemble learning.

Images