JP2021189979A - Information processing device, information processing method and information processing program - Google Patents

Abstract

To accurately visualize or/and digitizing a specific color region of an evaluation object imaged under various environmental light.SOLUTION: An information processing device includes an image acquisition part for acquiring a first image including an evaluation object having a specific color region in a ground color region, an image generation part for performing smoothing processing of the acquired first image and generating a second image, an image arithmetic part for subtracting or dividing each component of the first image and a component of the second image corresponding to each component of the first image and generating a third image, a threshold determination part for statistically processing a color distribution of an arbitrary region in the first image to calculate a statistic value, and determining a threshold for binarizing the third image on the basis of the statistic value, and an extraction part for extracting the specific color region with the third image as a binarized image obtained by correcting a variation component by using the determined threshold.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing apparatus for extracting a specific color region, an information processing method, and an information processing program.

In the above technical field, Patent Document 1 describes a technique for generating reference data used for image processing by generating difference data between image data having different resolutions and binarizing the generated difference data with a predetermined threshold value. Is disclosed.

Further, in Patent Document 2, in a color LCD panel, difference image data between original image data and shading image data is created in order to detect only color stains in which white defects are present in black defects. Then, the thresholds obtained empirically are applied to the created difference image data to create binary image data indicating the positions of the white defect and the black defect, respectively, and from the created binary image data, the inside of the black defect Discloses a technique for extracting only black defects including white defects.

Further, in Patent Document 3, in the mail processing apparatus, a dropout image and a non-dropout image of a letter are acquired in order to extract a postal code entry frame printed in red on the surface of the mail. Then, a technique is disclosed in which a red region is extracted by binarizing the pixel values of the corresponding pixels of a non-dropout image with a value obtained by subtracting an offset value from each pixel value of the dropout image as a threshold value.

Further, in Patent Document 4, in order to detect a stain defect, an average value, a standard deviation, a maximum value and a minimum value are calculated as statistical data of the luminance value of each pixel of the inspection target image, and the average value, the standard deviation, the maximum value and the minimum value are calculated from a predetermined calculation formula. A technique for automatically determining a white spot threshold and a black spot threshold is disclosed.

Japanese Unexamined Patent Publication No. 2008-99273 Japanese Unexamined Patent Publication No. 9-329527 Japanese Unexamined Patent Publication No. 8-98006 Japanese Unexamined Patent Publication No. 2004-226272

However, since the technique described in the above document does not consider the influence of the ambient light of the environment in which the evaluation object is imaged, the specific color region of the evaluation object imaged under various ambient lights is accurately visualized. Or / and could not be quantified.

Therefore, an object of the present invention is to provide a technique for solving the above-mentioned problems.

In order to achieve the above object, the information processing apparatus according to the present invention is
An image acquisition unit that acquires a first image including an evaluation object having a specific color region in the ground color region, and an image acquisition unit.
An image generation unit that smoothes the acquired first image to generate a second image,
An image calculation unit that generates a third image by subtracting or dividing each component of the first image and the component of the second image corresponding to each component of the first image.
A threshold value determining unit that statistically processes the color distribution of an arbitrary region in the first image to obtain a statistical value and determines a threshold value for binarizing the third image based on the statistical value.
Using the determined threshold value, the third image is used as a binarized image corrected for variable components, and an extraction unit for extracting the specific color region.
To prepare for.

In order to achieve the above object, the information processing method according to the present invention is:
An image acquisition step of acquiring a first image including an evaluation object having a specific color region in the ground color region, and
An image generation step of smoothing the acquired first image to generate a second image, and
An image calculation step for generating a third image by subtracting or dividing each component of the first image and the component of the second image corresponding to each component of the first image.
A threshold determination step of statistically processing the color distribution of an arbitrary region in the first image to obtain a statistical value and determining a threshold value for binarizing the third image based on the statistical value.
Using the determined threshold value, the third image is used as a binarized image corrected for variable components, and an extraction step of extracting the specific color region.
including.

In order to achieve the above object, the information processing program according to the present invention is
An image acquisition step of acquiring a first image including an evaluation object having a specific color region in the ground color region, and
An image generation step of smoothing the acquired first image to generate a second image, and
An image calculation step for generating a third image by subtracting or dividing each component of the first image and the component of the second image corresponding to each component of the first image.
A threshold determination step of statistically processing the color distribution of an arbitrary region in the first image to obtain a statistical value and determining a threshold value for binarizing the third image based on the statistical value.
Using the determined threshold value, the third image is used as a binarized image corrected for variable components, and an extraction step of extracting the specific color region.
Let the computer run.

According to the present invention, it is possible to accurately visualize and / or quantify a specific color region of an evaluation target imaged under various ambient lights.

It is a block diagram which shows the structure of the information processing apparatus which concerns on 1st Embodiment of this invention. It is a figure for demonstrating the outline of operation of the information processing apparatus which concerns on 2nd Embodiment of this invention. It is a block diagram for demonstrating the structure of the information processing apparatus which concerns on 2nd Embodiment of this invention. It is a figure for demonstrating an example of the threshold value table which the information processing apparatus which concerns on 2nd Embodiment of this invention has. It is a block diagram for demonstrating the hardware configuration of the information processing apparatus which concerns on 2nd Embodiment of this invention. It is a flowchart for demonstrating the processing procedure of the information processing apparatus which concerns on 2nd Embodiment of this invention. It is a block diagram for demonstrating the structure of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a figure for demonstrating an example of the scoring table which the information processing apparatus which concerns on 3rd Embodiment of this invention has. It is a block diagram for demonstrating the hardware configuration of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a flowchart for demonstrating the processing procedure of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a figure for demonstrating Example 1 of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a figure for demonstrating Example 1 of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a figure for demonstrating Example 2 of the information processing apparatus which concerns on 3rd Embodiment of this invention. It is a figure for demonstrating Example 3 of the information processing apparatus which concerns on 3rd Embodiment of this invention.

Hereinafter, embodiments for carrying out the present invention will be described in detail exemplary with reference to the drawings. However, the configurations, numerical values, processing flows, functional elements, and the like described in the following embodiments are examples, and the technical scope of the present invention is not intended to be limited to the following descriptions.

[First Embodiment]
The information processing apparatus 100 as the first embodiment of the present invention will be described with reference to FIG. The information processing device 100 is a device that extracts a specific color region from the acquired image.

The information processing apparatus 100 includes an image acquisition unit 101, an image generation unit 102, an image calculation unit 103, a threshold value determination unit 104, and an extraction unit 105. The image acquisition unit 101 acquires a first image 111 including an evaluation object having a specific color region in the ground color region. The image generation unit 102 smoothes the acquired first image 111 to generate a second image 121. The image calculation unit 103 generates the third image 131 by subtracting or dividing each component of the first image 111 and the component of the second image 121 corresponding to each component of the first image 111. The threshold value determination unit 104 statistically processes the color distribution of the arbitrary region in the first image 111 to obtain the statistical value 141, and determines the threshold value 142 for binarizing the third image 131 based on the statistical value 141. The extraction unit 105 uses the determined threshold value 142 to extract the specific color region 151 from the third image 131 as a binarized image corrected for variable components.

According to this embodiment, it is possible to accurately visualize and / or quantify a specific color region of an evaluation target imaged under various ambient lights.

[Second Embodiment]
Next, the information processing apparatus 200 according to the second embodiment of the present invention will be described with reference to FIGS. 2 to 6. An outline of the operation of the information processing apparatus 200 will be described with reference to FIG.

Using a mobile terminal 210 such as a smartphone or tablet terminal owned by the user, the user obtains an evaluation so that the evaluation target is placed in an area of more than half of the frame 211 displayed on the display of the mobile terminal 210. The evaluation object 220, which is the object to be evaluated, is imaged. In FIG. 2, the evaluation object 220 is the left forearm portion of the user, but the evaluation object 220 is not limited to this.

The mobile terminal 210 transmits the captured image 212 to the information processing device 200. The information processing apparatus 200 performs various image processing on the received image 212, and transmits the superimposed image 201 in which the specific color region 213 is superimposed on the image 212 to the mobile terminal 210.

The specific color region 213 may or may not be included in the frame 211, but it is preferable that the frame 211 is not included. Therefore, by displaying the frame 211 on the display of the mobile terminal 210, it is easy to identify which part of the image 212 the ground color region 214 is. Therefore, it is preferable that the frame 211 does not include the specific color region 213. Further, the size of the frame 211 is preferably 0.01% to 30% of all the pixels of the captured image 212, but includes 0.2% to 15% of all the pixels. Is more preferable. Further, it is preferable to take an image so that the evaluation object is contained in a region of half or more of the frame 211, but it is more preferable to take an image so that the evaluation object is contained in all the regions. The distance from the camera provided in the mobile terminal 210 to the evaluation object 220 is preferably 2 cm to 2 m, but it depends on the performance of the camera lens.

There are various conditions for the user to image the image 212 including the evaluation object 220. For example, the image is taken under outdoor sunlight, indoor fluorescent light, or LED (Light Emitting Diode) light. Or something. That is, the user takes an image of the evaluation object 220 under various lighting environments (ambient light), but the color tone of the specific color region 213 changes depending on the lighting environment, so the success or failure of the extraction of the specific color region 213 is , Depends on the lighting environment.

Therefore, in the information processing apparatus 200, the received image 212 is subjected to image processing for reducing the influence of the lighting environment. First, the information processing apparatus 200 corrects the illumination unevenness of the image 212 in order to reduce the unevenness due to the illumination. After that, the information processing apparatus 200 binarizes the illumination unevenness correction image using a threshold value to generate a binarized image, and extracts a specific color region 213 from the binarized image. Further, the ground color region 214 is extracted based on the color distribution of the region of the frame 211. Then, the information processing apparatus 200 generates a superimposed image 201 in which the specific color region 213 existing in the extracted ground color region 214 is superimposed on the image 212, and transmits the superimposed image 201 to the mobile terminal 210. The mobile terminal 210 displays the received superimposed image 201 on the display. As a result, the user can easily recognize in which portion of the evaluation object 220 the specific color region 213 exists.

Next, the configuration of the information processing apparatus 200 will be described with reference to FIG. The information processing apparatus 200 includes an image acquisition unit 301, an image generation unit 302, an image calculation unit 303, a threshold value determination unit 304, an extraction unit 305, and an output control unit 306.

The image acquisition unit 301 acquires an image 212 including an evaluation object 220 having a specific color region 213 in the ground color region 214. Although the specific color region 213 is described here as a reddish region, the color of the specific color region 213 is not limited to red. Further, the image 212 is an RGB image, which is an image in the RGB color space.

The image generation unit 302 smoothes the acquired image 212 to generate a smoothed image 321. Specifically, the image generation unit 302 first converts the RGB image 212 into an L ^* a ^* b ^* color space image L ^* a ^* b ^* image (hereinafter abbreviated as "Lab image"). Convert to.

Then, the image generation unit 302 converts the RGB image into a Lab image, and then performs a filter process on ^{the a * value of the converted Lab image.} Here, the filtering process is a smoothing process, and includes, for example, an average value filter, a Gaussian filter, a moving average filter, a median filter, a load average filter, a low pass filter, and the like. By the smoothing process, the brightness value of the image is leveled, and it can be used to reduce the brightness unevenness of the image.

The image conversion from the RGB image includes hue and color space conversion, such as L ^* a ^* b ^* conversion, grayscale conversion, HSV conversion, YCbCr conversion, XYZ conversion, L ^* u ^* v ^* conversion, and CMY conversion. It may be an HLS conversion, and is not limited to this. Then, by changing the image conversion (color conversion) to be used according to the color to be detected, the color to be detected can be reliably detected.

The image calculation unit 303 generates an image 331 (subtracted image) by subtracting or dividing each component of the image 212 and the component of the smoothed image 321 corresponding to each component of the image 212. Here, in the calculation by the image calculation unit 303, the smoothed image 321 may be subtracted or divided from the image 212, or conversely, the image 212 may be subtracted or divided from the smoothed image 321. The image calculation unit 303 subtracts or divides ^{the a *} image after the smoothing process from the image with ^{the a * value before the smoothing process.} As a result, the illumination unevenness of the image 212 can be corrected. For example, ^{when detecting a high redness based on the a *} value, it is preferable to subtract the smoothed image 321 from the image 212. The image to be smoothed may be an L ^* image or a b ^* image.

The threshold value determination unit 304 statistically processes the color distribution of the region of the frame 211 in the image 212 to obtain the statistical value 341, and determines the threshold value 342 for binarizing the image 331 based on the statistical value 341. The threshold value determination unit 304 determines the threshold value 342 corresponding to the median value (statistical value 341) of ^{the a *} value in the region of the frame 211 of the image obtained by converting the image 212 into a Lab image.

Here, the threshold value 342 is the number of values empirically determined with respect to the median of the a ^* value is derived from the result of the case of the threshold 342 value with respect to the median of the a ^* value .. For example, ^{an empirically obtained threshold value 342 is assigned to some of the medians of a *} values, and the threshold value 342 that gives the best result is plotted on the graph. Then, a calibration curve is derived from the threshold value 342 plotted on the graph by using various approximations such as exponential approximation, straight line approximation, logarithmic approximation, and polynomial approximation. As a result, the threshold value 342 corresponding to each of the median ^{a * values is derived.} In this way, ^{by determining the threshold value 342 corresponding to the median value of each a *} value in advance, it is not necessary to calculate the threshold value 342 each time.

The extraction unit 305 uses the determined threshold value 342 to correct the image 331 as a binarized image in which the influence of a component that fluctuates due to the influence of at least one of the ambient light condition and the camera parameter is reduced, as a specific color. Region 213 is extracted. Here, the correction of the fluctuation component means, for example, removing the influence of the color tone correction value (ambient light or white balance) from the image 331, but is not limited to this.

Further, the extraction unit 305 extracts the ground color based on the color distribution in the region of the frame 211. As a result, the ground color region 214 is determined. The extraction of the ground color region 214 is performed, for example, by converting the image 212, which is an RGB image, into an HSV image. That is, the ground color region 214 is extracted using the maximum value and the minimum value of each luminance value of the converted HSV image. Specifically, in the area of the frame 211, the minimum value of the H value -20 to the maximum value of the H value +20, the minimum value of the S value -20 to the maximum value of the S value +20, and the minimum value of the V value -20 to V. The range of the maximum value +20 of the value is taken as the ground color, and the area in this range is extracted as the binarized ground color area 214. Although the example described here by converting an RGB image into an HSV image and extracting the ground color region 214, the conversion method of the RGB image is not limited to the HSV conversion. In addition to using HSV conversion, for example, L ^* a ^* b ^* conversion, YCbCr conversion, XYZ conversion, L ^* u ^* v ^* conversion, CMY conversion and HLS conversion mean, median, mode, quartile. The ground color region 214 may be extracted from the quantiles, the third quartile, the standard deviation, the maximum value, the minimum value, the variance, and the like.

The output control unit 306 superimposes and outputs the specific color region 213 existing in the extracted ground color region 214 on the image 212. The mobile terminal 210 displays the superimposed image 201 output by the output control unit 306 on the display. The original image 212 on which the specific color region 213 is superimposed is not limited to a still image and may be a moving image. That is, the output control unit 306 may output an image in which the specific color region 213 is superimposed on the image captured by the user or the live image (image 212).

An example of the threshold table 401 included in the information processing apparatus 200 will be described with reference to FIG. The threshold table 401 stores the threshold 342 in association with the median 411. The median value 411 is the median value of the a ^* value. The threshold value 342 is a reference value used for binarizing the image 331 to obtain a binarized image. Then, the threshold value determination unit 304 determines the threshold value 342 with reference to the threshold value table 401.

The hardware configuration of the information processing apparatus 200 will be described with reference to FIG. The CPU (Central Processing Unit) 510 is a processor for arithmetic control, and realizes each functional configuration of the information processing apparatus 200 of FIG. 3 by executing a program. The CPU 510 has a plurality of processors, and different programs, modules, tasks, threads, and the like may be executed in parallel. The ROM (Read Only Memory) 520 stores fixed data such as initial data and programs, and other programs. Further, the network interface 530 communicates with other devices and the like via the network. The CPU 510 is not limited to one, and may be a plurality of CPUs or may include a GPU (Graphics Processing Unit) for image processing. Further, it is desirable that the network interface 530 has a CPU independent of the CPU 510 and writes or reads transmission / reception data in the area of the RAM (Random Access Memory) 540. Further, it is desirable to provide a DMAC (Direct Memory Access Controller) for transferring data between the RAM 540 and the storage 550 (not shown). Further, the CPU 510 recognizes that the data has been received or transferred to the RAM 540 and processes the data. Further, the CPU 510 prepares the processing result in the RAM 540, and the subsequent transmission or transfer is left to the network interface 530 or the DMAC.

The RAM 540 is a random access memory used by the CPU 510 as a temporary storage work area. The RAM 540 secures an area for storing data necessary for realizing the present embodiment. The image data 541 is data related to the image 212 acquired by the image acquisition unit 301. The smoothed image data 542 is data related to the smoothed image 321 obtained by smoothing the image 212. The subtraction / division image data 543 is data related to the image 331 obtained by subtracting or dividing each component of the image 212 and the corresponding component of the smoothed image 321. The threshold data 544 is data relating to the threshold value read from the threshold table 400. The binarized image data 545 is data relating to a binarized image obtained by binarizing the image 331 using the threshold value 342.

The transmission / reception data 546 is data transmitted / received via the network interface 530. Further, the RAM 540 has an application execution area 547 for executing various application modules.

The storage 550 stores a database, various parameters, and the following data or programs necessary for realizing the present embodiment. The storage 550 stores the threshold table 401. The threshold table 401 is a table that manages the relationship between the median value 411 and the threshold value 342 shown in FIG.

The storage 550 further stores an image acquisition module 551, an image generation module 552, an image calculation module 553, a threshold determination module 554, and an extraction module 555. The image acquisition module 551 is a module for acquiring an image 212 including an evaluation object 220 having a specific color region 213 in the ground color region 214. The image generation module 552 is a module that smoothes the image 212 to generate a smoothed image 321. The image calculation module 553 is a module that generates an image 331 by subtracting or dividing an image 212 and a smoothed image 321. The threshold value determination module 554 is a module that determines a threshold value 342 for binarizing the image 331 from the statistical value obtained by statistically processing the color distribution of the region of the frame 211 in the image 212. The extraction module 555 is a module that extracts a specific color region 213 as a binarized image in which the image 331 is corrected for fluctuation components by using the threshold value 342. The extraction module 555 is a module that extracts the ground color region 214 based on the color distribution of the region of the frame 211. These modules 551 to 555 are read by the CPU 510 into the application execution area 547 of the RAM 540 and executed. The control program 556 is a program for controlling the entire information processing apparatus 200.

The input / output interface 560 interfaces input / output data with an input / output device. A display unit 561 and an operation unit 562 are connected to the input / output interface 560. Further, a storage medium 564 may be further connected to the input / output interface 560. Further, a speaker 563 which is an audio output unit, a microphone (not shown) which is an audio input unit, or a GPS position determination unit may be connected. The RAM 540 and the storage 550 shown in FIG. 5 do not show programs or data related to general-purpose functions and other feasible functions of the information processing apparatus 200.

The processing procedure of the information processing apparatus 200 will be described with reference to the flowchart of FIG. This flowchart is executed by the CPU 510 of FIG. 5 using the RAM 540, and realizes each functional configuration of the information processing apparatus 200 of FIG. In step S601, the image acquisition unit 301 acquires the image 212. In step S603, the image generation unit 302 smoothes the image 212 to generate a smoothed image 321. In step S605, a division / division image is generated. In step S607, the threshold value determination unit 304 statistically processes the color distribution of the region of the frame 211 in the image 212 to obtain the statistical value 341. In step S609, the threshold value determination unit 304 determines the threshold value 342 based on the statistical value 341. In step S611, the extraction unit 305 generates a binarized image in which the variation component is corrected from the image 331. In step S613, the extraction unit 305 extracts the specific color region 213. In step S615, the extraction unit 305 extracts the ground color region 214. In step S617, the output control unit 306 outputs the superimposed image 201.

According to the present embodiment, since the specific color region 213 included in the evaluation object 220 is superimposed and displayed on the original image 212, the location where the specific color region 213 exists can be easily visually recognized. Further, since the specific color region 213 is extracted by eliminating the influence of the lighting environment, the specific color region 213 can be extracted with high accuracy in any lighting environment.

In the above description, the information processing device 200 has been described by taking a server as an example, but each functional configuration included in the information processing device 200 may be mounted on, for example, a smartphone, a tablet terminal, or a PC (Personal Computer). good. When each functional configuration is implemented in a mobile terminal such as a smartphone or tablet terminal, communication between the mobile terminal and the server becomes unnecessary.

[Third Embodiment]
Next, the information processing apparatus 700 according to the third embodiment of the present invention will be described with reference to FIGS. 7 to 10. FIG. 7 is a block diagram showing the configuration of the information processing apparatus 700 according to the present embodiment. The information processing apparatus 700 according to the present embodiment is different from the second embodiment in that it has a scoring unit 701. Since other configurations and operations are the same as those in the second embodiment, the same configurations and operations are designated by the same reference numerals and detailed description thereof will be omitted.

The information processing apparatus 700 has a scoring unit 701. The scoring unit 701 scores the degree of existence of the specific color region 213 based on the ratio of the specific color region 213 to the ground color region 214. Specifically, the scoring unit 701 calculates the score (S) based on the ratio (P) of the specific color region 213 to the ground color region 214. The scoring unit 701 is, for example, S = 0 when P = 0 to 0.1%, S = 1 when P = 0.1% to 1.0%, and P = 1.0% to 5. In the case of 0%, S = 2, and in the case of P> 5.0%, S = 3. Here, the evaluation is made on a 4-point scale of 0 to 3, but for example, a 10-point evaluation, a rank evaluation such as A to E, or a score evaluation of 0 to 100 is also possible. Well, but not limited to these.

An example of the scoring table 801 included in the information processing apparatus 700 will be described with reference to FIG. The scoring table 801 stores the score 812 in association with the specific color region ratio 811. The specific color region ratio 811 is the ratio (P) of the specific color region 213 to the ground color region 214. The score 812 is a value determined based on the ratio (P). Here, scoring is performed in four stages from 0 to 3, but the scoring method is not limited to this.

The hardware configuration of the information processing apparatus 700 will be described with reference to FIG. 9. The RAM 940 is a random access memory used by the CPU 510 as a temporary storage work area. The RAM 940 secures an area for storing data necessary for realizing the present embodiment. The ratio data 941 is data representing the ratio of the specific color region 213 to the ground color region 214. The score data 942 is data relating to the score determined corresponding to the ratio (P).

The storage 950 stores the scoring table 801. The scoring table 801 is a table that manages the relationship between the specific color region ratio 811 and the score 812. The storage 950 further stores the scoring module 951. The scoring module 951 is a module for scoring the degree of existence of the specific color region 213 based on the ratio of the specific color region 213 to the ground color region 214.

The processing procedure of the information processing apparatus 700 will be described with reference to the flowchart of FIG. This flowchart is executed by the CPU 510 of FIG. 9 using the RAM 940, and realizes each functional configuration of the information processing apparatus 700 of FIG. In step S1001, the scoring unit 701 calculates the ratio of the specific color region 213 to the ground color region 214. In step S1003, the scoring unit 701 scores the degree of existence of the specific color region 213 based on the calculated ratio. In step S1005, the output control unit 306 further superimposes the score on the superposed image 201 and outputs the score.

According to this embodiment, since the ratio of the specific color region of the evaluation target is scored, the degree of skin improvement can be easily grasped.

[Example 1]
Next, the first embodiment of the present embodiment will be described with reference to FIGS. 11A to 11B. In this embodiment, an example of extracting a reddish region (specific color region 213) of the skin region (ground color region 214) will be described. The information processing apparatus 700 converts a skin image showing the skin from an RGB image to a Lab image (1101 → 1102). Next, the information processing apparatus 700 performs a smoothing process as a filter process on ^{the a * value of the converted Lab image (1103).} Then, the information processing apparatus 700, to the pre-smoothing process ^{a *} value image (1102), subtracts the post-smoothing ^{a *} value image (1103) (1104). The color distribution of an arbitrary region (the region of the frame 211) of the image is statistically processed to obtain a statistical value, and a threshold value 342 for binarization is calculated based on the obtained statistical value (1105). In the calculation of the threshold value 342, the threshold value 342 is set so that the area of the specific color region existing in the same image shot under different shooting conditions in advance becomes the same value according to the median a * value of the region of each frame 211. Is assigned, a calibration curve 1151 is created, and a threshold value 342 is calculated from the created calibration curve 1151. Then, the subtracted image (1104) is binarized using the calculated threshold value 342 to detect the reddish region (1104 → 1106). That is, in the subtracted image (1104), a binarized image (1106) is generated by distinguishing a pixel having a value equal to or more than a predetermined luminance value and a pixel having a value less than a predetermined luminance value. , Detects reddish areas.

Next, the information processing apparatus 700 generates a binarized image in which the skin region is detected from the color distribution of the arbitrary region (the region of the frame 211) of the image in which the skin is captured (1101 → 1108). The detection of the skin region is performed using an image obtained by converting an RGB image into an HSV image. The skin region is, for example, from the minimum value of H value -20 to the maximum value of H value +20 in the arbitrary region (the region of the frame 211), the minimum value of S value -20 to the maximum value of S value +20, and the V value. It is detected as a region in the range of the minimum value -20 to the minimum value +20 of the V value. Then, the image in which the reddish region is detected is multiplied by the image in which the skin portion is detected (1106 × 1108 = 1109). As a result, an image containing only the reddish region can be obtained. Then, the information processing apparatus 700 superimposes the obtained image of the reddish region (1109) on the original image (1101) and outputs the superposed image 201. Next, the information processing apparatus 700 calculates the ratio of the area of the reddish region (1109) to the area of the skin color region (1108). Then, the redness score is determined according to the calculated ratio of the redness region. The determined redness score is output together with the superimposed image 201.

[Example 2]
Next, a second embodiment of the present embodiment will be described with reference to FIG. This embodiment is an example of extracting a reddish region (specific color region 213) of a skin region (ground color region 214) under three different ambient lights. The upper part of FIG. 12 is an image captured by the user, and the lower part of FIG. 12 is a diagram showing a detection result. Since the process of detecting the reddish region is the same as that of the first embodiment, the description thereof is omitted and only the result is presented.

Here, the image 1201 is an artificial light source environment, and is an image captured under daylight color illumination (color temperature: 5700K to 7100K). Image 1202 is a natural light source environment and is imaged under sunlight (color temperature: 5000K to 6000K), and image 1203 is an artificial light source environment and is imaged under light bulb color lighting (color temperature: 2600K to 3250K). It is an image. As shown in the lower part of FIG. 12, even under various ambient lights, the reddish region can be accurately detected and output as a superposed image 1204, 1205, 1206.

[Example 3]
Next, a third embodiment of the present embodiment will be described with reference to FIG. This embodiment is an example of extracting a reddish region (specific color region 213) from a skin region (ground color region 214) under three different ambient lights. Unlike the second embodiment, this embodiment is different from the second embodiment in that the reddish region (specific color region 1311, 1321, 1331) is reflected in the frame 211 of the image captured under various ambient lights. Is an example of extracting. The upper part of FIG. 13 is an image captured by the user, and the lower part of FIG. 13 is a diagram showing a detection result. Since the process of detecting the reddish region is the same as that of the first embodiment, the description thereof is omitted and only the result is presented.

Here, the ambient light in the images 1301, 1302, 1303 corresponds to each of the images 1201, 1202, 1203 shown in FIG. Then, as shown in the lower part of FIG. 13, even if the reddish region is included in the frame 211, the reddish region can be accurately detected and output as superimposed images 1304, 1305, 1306.

[Other embodiments]
Although the invention of the present application has been described above with reference to the embodiments, the invention of the present application is not limited to the above-described embodiment. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the configuration and details of the present invention. Also included in the scope of the present invention are systems or devices in which the different features contained in each embodiment are combined in any way.

Further, the present invention may be applied to a system composed of a plurality of devices, or may be applied to a single device. Furthermore, the present invention is also applicable when the information processing program that realizes the functions of the embodiment is directly or remotely supplied to the system or device. Therefore, in order to realize the functions of the present invention on a computer, a program installed on the computer, a medium containing the program, and a WWW (World Wide Web) server for downloading the program are also included in the scope of the present invention. .. In particular, at least a non-transitory computer readable medium containing a program for causing a computer to execute the processing steps included in the above-described embodiment is included in the scope of the present invention.

100 Information processing device 101 Image acquisition unit 111 Image acquisition unit 111 First image 102 Image generation unit 121 Second image 103 Image calculation unit 131 Third image 104 Threshold determination unit 141 Statistical value 142 Threshold 105 Extraction unit 151 Specific color area 200 Information processing device 201 Superimposition Image 210 Mobile terminal 211 Frame 212 Image 213 Specific color area 214 Ground color area 220 Evaluation target 301 Image acquisition unit 302 Image generation unit 321 Smoothed image 303 Image calculation unit 331 Image 304 Threshold determination unit 341 Statistical value 342 Threshold 305 Extraction unit 351 Superimposed image 306 Output control unit 401 Threshold table 510 CPU
520 ROM
530 network interface 540 RAM
550 Storage 560 I / O interface 700 Information processing device 701 Scoring unit 801 Scoring table 940 RAM
950 storage

Claims (13)

An image acquisition unit that acquires a first image including an evaluation object having a specific color region in the ground color region, and an image acquisition unit.
An image generation unit that smoothes the acquired first image to generate a second image,
An image calculation unit that generates a third image by subtracting or dividing each component of the first image and the component of the second image corresponding to each component of the first image.
A threshold value determining unit that statistically processes the color distribution of an arbitrary region in the first image to obtain a statistical value and determines a threshold value for binarizing the third image based on the statistical value.
Using the determined threshold value, the third image is used as a binarized image corrected for variable components, and an extraction unit for extracting the specific color region.
Information processing device equipped with. The information processing device according to claim 1, wherein the extraction unit extracts the ground color region based on the color distribution of the arbitrary region. The first image is an RGB image and is an RGB image.
The information processing apparatus according to claim 2, wherein the extraction unit extracts the ground color region after converting an RGB image into an HSV image. The information processing apparatus according to any one of claims 1 to 3, further comprising an output control unit that superimposes and outputs the specific color region existing in the extracted ground color region on the first image. The information processing apparatus according to any one of claims 1 to 4, further comprising a scoring unit for scoring the degree of existence of the specific color region based on the ratio of the specific color region to the ground color region. Any of claims 1 to 5, wherein the threshold value determination unit determines the threshold value from the statistical value obtained by the threshold value determination unit based on a predetermined relationship between the statistical value and the threshold value. The information processing apparatus according to item 1. The first image is an RGB image and is an RGB image.
The information processing apparatus according to any one of claims 1 to 6, wherein the image generation unit performs smoothing processing after converting an RGB image into an L ^* a ^* b ^{* image.} The information processing apparatus according to any one of claims 1 to 7, wherein the color distribution is an L ^* a ^* b ^{* image.} The information processing apparatus according to claim 8, wherein the statistical value is the median value of a ^{* value.} The information processing apparatus according to any one of claims 1 to 9, wherein the image generation unit ^{performs smoothing processing on any one of L *} image, a ^* image, and b ^{* image.} The information processing apparatus according to any one of claims 1 to 10, wherein the variable component is a component that fluctuates due to the influence of at least one of an ambient light condition and a camera parameter. An image acquisition step of acquiring a first image including an evaluation object having a specific color region in the ground color region, and
An image generation step of smoothing the acquired first image to generate a second image, and
An image calculation step for generating a third image by subtracting or dividing each component of the first image and the component of the second image corresponding to each component of the first image.
A threshold determination step of statistically processing the color distribution of an arbitrary region in the first image to obtain a statistical value and determining a threshold value for binarizing the third image based on the statistical value.
Using the determined threshold value, the third image is used as a binarized image corrected for variable components, and an extraction step of extracting the specific color region.
Information processing methods including. An image acquisition step of acquiring a first image including an evaluation object having a specific color region in the ground color region, and
An image generation step of smoothing the acquired first image to generate a second image, and
An image calculation step for generating a third image by subtracting or dividing each component of the first image and the component of the second image corresponding to each component of the first image.
A threshold determination step of statistically processing the color distribution of an arbitrary region in the first image to obtain a statistical value and determining a threshold value for binarizing the third image based on the statistical value.
Using the determined threshold value, the third image is used as a binarized image corrected for variable components, and an extraction step of extracting the specific color region.
An information processing program that causes a computer to execute.

Images