Specification
Title of Invention: Face Recognition Environment Determination Method, Face Recognition Environment Determination System, Face Recognition Environment Determination Apparatus, and Non-Temporary Computer-Readable Medium
Technical field
[0001]
The present disclosure relates to a face authentication environment determination method, a face authentication environment determination system, a face authentication environment determination device, and a non-transitory computer-readable medium.
Background technology
[0002]
In recent years, face authentication systems have been developed that identify a person using a face image captured by a camera. Here, in a face image of a person with white skin such as Caucasian (Caucasian), overexposure tends to occur in a bright environment, and in a face image of a person with dark skin such as black (Negroid), it is dark. Black crushing is likely to occur in the environment.
[0003]
If such blown-out highlights or blocked-up shadows occur in the face image, face recognition may not be performed accurately. Therefore, for example, when installing a camera for a face authentication system, it is necessary to determine whether the environment for performing face authentication (hereinafter referred to as face authentication environment) is appropriate. The face authentication environment changes depending on, for example, the installation position and orientation of the camera, the brightness of the location where the image is taken, and the like.
[0004]
By the way, Patent Document 1 discloses a skin color chart for skin color reproduction evaluation in color photographs and the like.
In this specification, the terms “black (Negroid),” “white (Caucasoid),” and “yellow (Mongoloid)” are used to express differences in skin color. I have no intention of doing so.
prior art documents
patent literature
[0005]
Patent Document 1: JP-A-2001-074556
SUMMARY OF THE INVENTION
Problems to be Solved by the Invention
[0006]
The inventor found the following issues regarding face authentication environment determination.
　There was a problem that it was not convenient from various points of view to have white and black people actually present each time the face recognition environment was determined.
It should be noted that the skin color chart disclosed in Patent Document 1 is for evaluation of skin color reproduction in color photographs and the like, and does not disclose or suggest face authentication at all.
[0007]
In view of such problems, the present disclosure aims to provide a highly convenient face authentication environment determination method.
Means to solve problems
[0008]
The face authentication environment determination method according to the present disclosure is
A skin color chart in which a first skin color display unit representing a Negroid skin color and a second skin color display unit representing a Caucasian skin color are formed on a substrate is imaged,
Analyzing the brightness of the first and second skin color display parts in the captured image of the skin color chart,
　Based on the brightness of the first and second skin color display units, it is determined whether or not the imaging environment of the image is suitable for face authentication.
[0009]
The face authentication environment determination system according to the present disclosure is
a skin color chart formed on a substrate with a first skin color display portion representing a negroid skin color and a second skin color display portion representing a caucasian skin color;
an imaging means for imaging the skin color chart;
an image analysis means for analyzing the brightness of the first and second skin color display parts in the image of the skin color chart captured by the imaging means;
environment determination means for determining whether or not the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units.
[0010]
The face authentication environment determination device according to the present disclosure is
Analyzing the brightness of the first and second skin color display portions in the image of the skin color chart in which the first skin color display portion representing the Negroid skin color and the second skin color display portion representing the Caucasian skin color are formed on a substrate. an image analysis means for
environment determination means for determining whether or not the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units.
[0011]
The non-transitory computer-readable medium according to the present disclosure is
Analyzing the brightness of the first and second skin color display portions in the image of the skin color chart in which the first skin color display portion representing the Negroid skin color and the second skin color display portion representing the Caucasian skin color are formed on a substrate. death,
Determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units,
It contains a face authentication environment determination program that causes a computer to execute processing.
[0012]
Another face authentication environment determination method according to the present disclosure is
Analyzing the brightness of the first and second skin color display portions in the image of the skin color chart in which the first skin color display portion representing the Negroid skin color and the second skin color display portion representing the Caucasian skin color are formed on a substrate. death,
　Based on the brightness of the first and second skin color display units, it is determined whether or not the imaging environment of the image is suitable for face authentication.
Effect of the invention
[0013]
According to the present disclosure, it is possible to provide a highly convenient face authentication environment determination method.
Brief description of the drawing
[0014]
1 is a block diagram showing the configuration of a face authentication environment determination system according to a first embodiment; FIG.
2 is a plan view showing a skin color chart 10 in the face authentication environment determination system according to the first embodiment; FIG.
3 is a graph showing an example of spectral reflectance of skin colors of black, white, and yellow people. FIG.
4 is a flowchart showing a face authentication environment determination method according to the first embodiment; FIG.
5 is a plan view showing a skin color chart 10 in the face authentication environment determination system according to the second embodiment; FIG.
6 is a block diagram showing the configuration of a face authentication environment determination system according to a third embodiment; FIG.
7 is a plan view showing a skin color chart 10 in the face authentication environment determination system according to the third embodiment; FIG.
8 is a flowchart showing a face authentication environment determination method according to the third embodiment; FIG.
9 is a plan view showing a skin color chart in the face authentication environment determination system according to the fourth embodiment; FIG.
10 is a plan view showing a skin color chart in the face authentication environment determination system according to the fifth embodiment; FIG.
MODE FOR CARRYING OUT THE INVENTION
[0015]
Specific embodiments will be described in detail below with reference to the drawings. In each drawing, the same reference numerals are given to the same or corresponding elements, and redundant description will be omitted as necessary for clarity of description.
[0016]
(First embodiment)

First, the face authentication environment determination system according to the first embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of the face authentication environment determination system according to the first embodiment. The system determines whether or not the environment is suitable for face recognition, in which the face image of a person with fair skin does not suffer from overexposure, and the face of a person with dark skin does not suffer from blackout. .
As shown in FIG. 1, the face authentication environment determination system according to the first embodiment includes a skin color chart 10, a camera 20, and a face authentication environment determination device 100.
[0017]
Here, FIG. 2 is a plan view showing the skin color chart 10 in the face authentication environment determination system according to the first embodiment.
As shown in FIG. 2, in the skin color chart 10, a first skin color display portion BK representing black (negroid) skin color and a second skin color display portion WT representing white (caucasian) skin color are formed on a substrate. ing. Details of the skin color chart 10 will be described later.
The camera 20 is imaging means for capturing an image of the skin color chart 10 .
[0018]
The face authentication environment determination device 100 includes an image analysis unit 110 and an environment determination unit 120.
Note that the face authentication environment determination apparatus 100 is realized by a computer device such as a personal computer or a server that executes a program, for example, but it may be realized by one device or by a plurality of devices on a network. may Also, the camera 20 may be provided inside the face authentication environment determination device 100 .
[0019]
The image analysis unit 110 is communicatively connected to the camera 20. A wired connection or a wireless connection may be used. The image analysis unit 110 analyzes the brightness of the first skin color display portion BK and the second skin color display portion WT in the image of the skin color chart 10 captured by the camera 20 . For example, the image analysis unit 110 quantifies the brightness of the first skin color display portion BK and the second skin color display portion WT in the image of the skin color chart 10 into 256 levels from 0 to 255. FIG. Normally, the brightness of the second skin color display portion WT showing white skin color is higher than that of the first skin color display portion BK showing black skin color, and the luminance value of 0 to 255 is also higher.
[0020]
The environment determination unit 120 determines whether the imaging environment is suitable for face authentication based on the brightness of the first skin color display unit BK and the second skin color display unit WT. For example, the environment determination unit 120 determines that the luminance values ​​of the first skin color display portion BK and the second skin color display portion WT are suitable for face authentication if they are within predetermined reference ranges. Conversely, if at least one of the luminance values ​​of the first skin color display portion BK and the second skin color display portion WT is outside the above-described reference range, the environment determination section 120 determines that it is not suitable for face authentication.
[0021]
The reference range is predetermined as a range of luminance values ​​suitable for face authentication. Qualitatively, it is a luminance value range in which neither blackening nor whiteout occurs. A specific numerical range is appropriately determined based on the performance of the camera to be used and the face recognition engine. The reference range data is stored in a storage unit (not shown) in the face authentication environment determination device 100, for example. The storage unit may be provided inside the environment determination unit 120 or may be provided outside.
[0022]
In the face recognition environment determination system according to the first embodiment, instead of using actual images of white and black people, a first skin color display portion BK representing a black skin color and a second skin color representing a white skin color are displayed. An image of the skin color chart 10 on which the display portion WT is formed is used. Therefore, when determining the face authentication environment, it is not necessary to have white and black people actually present, which is very convenient.
[0023]

Next, the details of the skin color chart 10 will be described with reference to FIG.
The substrate 11 is made of, but not limited to, cardboard, plastic, wood, metal, glass, and combinations thereof. Constructing the substrate 11 from cardboard, plastic or wood makes it lightweight and therefore easy to carry. In the example shown in FIG. 2, the substrate 11 has a rectangular planar shape, but it is not limited at all. The size of the substrate 11 is also not particularly limited, but as an example, it is about 200 mm wide and about 300 mm long. The color of the substrate 11 is also not particularly limited, but from the viewpoint of preventing reflection, it is preferably black with a reflectance of 0, for example.
[0024]
The color of the first skin color display portion BK is not particularly limited as long as it represents the skin color of black people. However, if the color of the first skin color display portion BK is, for example, a standard black skin color, face recognition may not be performed accurately. Specifically, even if the environment is determined to be suitable for face authentication, the environment is actually too dark. can occur.
[0025]
Therefore, the first skin color display section BK may indicate a skin color near the blackest limit in the skin color distribution of blacks (negroids). Specifically, colors can be defined using the CIE L*a*b* color space standardized in 1976 by the International Commission on Illumination (CIE). The lightness L* of the skin color in the first skin color display portion BK represented in the CIE L*a*b* color space satisfies, for example, 20≦L*≦37. A normal black skin tone is lighter and has an L* value greater than 37. More preferably, 20≦L*≦29.
Also, the chromaticities a* and b* of the first skin color display portion BK satisfy, for example, 8≦a*≦12 and 7≦b*≦10. More preferably, 9≦a*≦11 and 8≦b*≦9.
In the example shown in FIG. 2, the first skin color display portion BK has a square planar shape, but is not limited in any way.
[0026]
The color of the second skin color display portion WT is not particularly limited as long as it represents the skin color of white people. However, if the color of the second skin color display portion WT is, for example, a standard white skin color, face recognition may not be performed accurately. . Specifically, even if the environment is determined to be suitable for face authentication, the environment is actually too bright, and in the face image of a person whose fair complexion is lighter than that of the second skin color display portion WT, whiteout occurs. can occur.
[0027]
Therefore, the second skin color display part WT may indicate a skin color near the whitest limit in the distribution of white (Caucasian) skin colors. Specifically, the lightness L* of the skin color in the second skin color display portion WT expressed in the CIE L*a*b* color space satisfies, for example, 74≦L*≦81. A normal Caucasian skin tone is darker and has an L* value less than 74. More preferably, 78≦L*≦81.
Also, the chromaticities a* and b* of the second skin color display portion WT satisfy, for example, 10≦a*≦12 and 23≦b*≦25. More preferably, a*=11 and b*=24.
In the example shown in FIG. 2, the first skin color display portion BK has a square planar shape, but is not limited in any way.
[0028]
Here, FIG. 3 is a graph showing an example of spectral reflectance of skin colors of black, white, and yellow people. In FIG. 3, the horizontal axis indicates wavelength (nm), and the vertical axis indicates spectral reflectance. As shown in FIG. 3, at each wavelength, the spectral reflectance increases in the order of black people, yellow people, and white people. For example, when measured using a spectrophotometer, the spectral reflectance data shown in FIG. 3 and the corresponding L*, a*, and b* values ​​in the CIE L*a*b* color space are can get. For a large number of blacks and whites, skin color L*, a*, b* data can be obtained to determine the above ranges.
[0029]
As described above, when the first skin color display portion BK in the skin color chart 10 indicates a skin color near the blackest limit in the skin color distribution of black people, the person whose face is darker than the first skin color display portion BK The possibility of being subject to certification is extremely low. Therefore, in an environment determined to be suitable for face authentication using such a skin color chart 10, the possibility that black crushing occurs in the face image and face authentication is not possible is extremely low.
[0030]
Similarly, when the second skin color display portion WT in the skin color chart 10 indicates a skin color near the whitest limit in the skin color distribution of Caucasians, a person who is fairer than the second skin color display portion WT is eligible for face recognition. The possibility of becoming a target is extremely low. Therefore, in an environment determined to be suitable for face recognition using such a skin color chart 10, there is a very low possibility that the face image will be overexposed and face recognition will not be possible.
From the above, using such a skin color chart 10 makes it possible to more appropriately determine the face authentication environment.
[0031]

Next, referring to FIG. 2, a method for manufacturing a skin color chart according to the first embodiment will be described. A first skin color display portion BK is formed on the substrate 11, and a second skin color display portion WT is formed. Either the first skin color display portion BK or the second skin color display portion WT may be formed first on the substrate 11, or both may be formed at the same time.
[0032]
A specific example of the skin color chart manufacturing method according to the first embodiment will be described below, but the method is not limited to this specific example.
First, a first skin color display portion BK and a second skin color display portion WT prepared in advance are pasted on a mount made of cardboard. For example, the first skin color display portion BK and the second skin color display portion WT can be prepared by applying paints adjusted to the respective colors on paper. Although the paint is not particularly limited, it is, for example, a matte lacquer paint.
[0033]
Next, prepare a black cardboard of the same size as the mount, and cut out portions corresponding to the first skin color display portion BK and the second skin color display portion WT attached to the mount. Then, this black cardboard and the mount on which the first skin color display portion BK and the second skin color display portion WT are pasted are pasted together. Here, the black cardboard was processed so that the surface reflectance was 0 (zero).
By the above, the skin color chart 10 can be manufactured. In the skin color chart 10 produced according to this embodiment, the substrate 11 is composed of a backing paper and a black cardboard.
[0034]

Next, a face authentication environment determination method according to the first embodiment will be described with reference to FIG. FIG. 4 is a flow chart showing the face authentication environment determination method according to the first embodiment. In the description of FIG. 4, FIG. 1 and FIG. 2 will be referred to as appropriate.
[0035]
First, as shown in FIG. 4, the camera 20 takes an image of the skin color chart 10 in which the first skin color display portion BK and the second skin color display portion WT are formed on the substrate 11 (step ST1).
Next, the image analysis unit 110 analyzes the brightness of the first skin color display portion BK and the second skin color display portion WT in the captured image of the skin color chart (step ST2).
[0036]
Next, the environment determination unit 120 determines whether the imaging environment of the image is suitable for face authentication based on the brightness of the first skin color display unit BK and the second skin color display unit WT. Specifically, as shown in FIG. 4, it is determined whether or not the luminance of the first skin color display portion BK and the second skin color display portion WT is within a predetermined reference range (step ST3).
[0037]
If the luminance values ​​of the first skin color display portion BK and the second skin color display portion WT are within the respective predetermined reference ranges (step ST3 YES), it is determined that the imaging environment is suitable for face authentication (step ST4). . If at least one of the luminance values ​​of the first skin color display portion BK and the second skin color display portion WT is out of the reference range (NO in step ST3), it is determined that the imaging environment is not suitable for face authentication (step ST5). ).
[0038]
In the face authentication environment determination method according to the first embodiment, instead of using actual images of white and black people, a first skin color display portion BK representing a black skin color and a second skin color representing a white skin color are displayed. An image of the skin color chart 10 on which the display portion WT is formed is used. Therefore, when determining the face authentication environment, it is not necessary to have white and black people actually present, which is very convenient.
[0039]
(Second embodiment)
Next, a skin color chart in the face authentication environment determination system according to the second embodiment will be described with reference to FIG. FIG. 5 is a plan view showing the skin color chart 10 in the face authentication environment determination system according to the second embodiment.
In the skin color chart 10 in the face authentication environment determination system according to the first embodiment shown in FIG. 2, the first skin color display portion BK and the second skin color display portion WT are formed planarly (flatly). was On the other hand, in the skin color chart 10 in the face authentication environment determination system according to the second embodiment shown in FIG. It is formed in a three-dimensional shape. That is, in the first skin color display portion BK and the second skin color display portion WT, unevenness that imitates a human face is formed.
[0040]
When the skin color chart 10 shown in FIG. 2 is used, even in an environment that is determined to be suitable for face authentication, for example, in a face image of a black person, black crushing occurs in a concave part of the face (for example, near the shadow of the nose). It may occur and face authentication may not be possible. Alternatively, for example, whitening may occur in a convex portion of the face (for example, near the top of the nose) in a Caucasian face image, and face authentication may not be possible.
[0041]
On the other hand, when the skin color chart 10 shown in FIG. 5 is used, when the face authentication environment is determined, the recesses of the first skin color display portion BK having a three-dimensional shape that imitates a human face, etc., black crushing occurs. It can be determined that the environment where In addition, it is possible to determine that an environment in which overexposure occurs in the projections of the second skin color display unit WT having a three-dimensional shape that resembles a human face is also inappropriate.
Therefore, by using the skin color chart 10 according to the present embodiment, the face authentication environment can be determined more appropriately.
Other configurations are the same as those of the first embodiment, so descriptions thereof are omitted.
[0042]
(Third embodiment)
Next, a face authentication environment determination system according to the third embodiment will be described with reference to FIG. FIG. 6 is a block diagram showing the configuration of a face authentication environment determination system according to the third embodiment. As shown in FIG. 6, the face authentication environment determination system according to this embodiment includes a face authentication environment determination device 200 instead of the face authentication environment determination device 100 shown in FIG. .
The face authentication environment determination device 200 includes a dynamic range determination unit 130 and an image acquisition unit 140 in addition to the image analysis unit 110 and the environment determination unit 120 shown in FIG.
[0043]
Here, the skin color chart in the face authentication environment determination system according to the third embodiment will be described with reference to FIG. FIG. 7 is a plan view showing a skin color chart in the face authentication environment determination system according to the third embodiment.
The skin color chart 10 shown in FIG. 7 includes, in addition to the skin color chart 10 shown in FIG. 2, grayscale sections GS1 and GS2 each composed of a plurality of gray display sections GR having different reflectances.
[0044]
In the example shown in FIG. 7, each of the two gray scale sections GS1 and GS2 has ten gray display sections GR each having a reflectance of 2 to 90%. Specifically, the reflectance of each gray display portion GR is 2%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, and 90%.
[0045]
In the example shown in FIG. 7, ten gray display parts GR are arranged in a row along the long side of the rectangular skin color chart 10 in the grayscale parts GS1 and GS2. Also, the gray scale sections GS1 and GS2 are arranged opposite to each other with the first skin color display section BK and the second skin color display section WT interposed therebetween.
[0046]
Return to Figure 6 to continue the explanation.
Also in the face authentication environment determination device 200 according to the present embodiment, the image analysis unit 110 analyzes the brightness of the first skin color display portion BK and the second skin color display portion WT in the image of the skin color chart 10 . Furthermore, the image analysis unit 110 also analyzes the brightness of the plurality of gray display portions GR in the gray scale portions GS1 and GS2. For example, the image analysis unit 110 quantifies the brightness of each of the 20 gray display areas GR in the image of the skin color chart 10 into 256 levels from 0 to 255. FIG. Normally, the higher the reflectance of 2% to 90% of each gray display portion GR, the higher the luminance value of each gray display portion GR.
[0047]
The dynamic range determination unit 130 determines whether or not the dynamic range is appropriate based on the brightness of the 20 gray display portions GR in the image of the skin color chart 10 . For example, the dynamic range determination unit 130 determines that the dynamic range is inappropriate when adjacent gray display portions GR have the same luminance value. Further, when the luminance value of the gray display portion GR having the higher reflectance is lower than the luminance value of the gray display portion GR having the lower reflectance among the adjacent gray display portions GR, the dynamic range is determined to be inappropriate. do.
[0048]
As a specific example, when the luminance values ​​of adjacent gray display portions GR having a reflectance of 90% and 80% are both the maximum value of 255, the dynamic range determination unit 130 determines that the dynamic range is inappropriate. Alternatively, when the brightness values ​​of the adjacent gray display portions GR having a reflectance of 2% and 10% are both the lowest value of 0, the dynamic range determination section 130 determines that the dynamic range is inappropriate.
The display unit 30 displays the determination result of the environment determination unit 120 and the determination result of the dynamic range determination unit 130.
[0049]
The image acquisition unit 140 is communicably connected to the camera 20 . A wired connection or a wireless connection may be used. The image acquisition unit 140 acquires the image of the skin color chart 10 captured by the camera 20 . Then, the image analysis unit 110 analyzes the brightness of the first skin color display portion BK and the second skin color display portion WT in the image of the skin color chart 10 acquired by the image acquisition unit 140 . In this manner, the image analysis section 110 may acquire and analyze the image of the skin color chart 10 via the image acquisition section 140 .
[0050]
In the example shown in FIG. 7, each gray display portion GR has a square planar shape, but is not limited in any way. Also, the number of gray display portions GR included in the gray scale portions GS1 and GS2 and the reflectance of each gray display portion GR may be appropriately determined. moreover, and the number of grayscale portions may be one.
Other configurations are the same as those of the first embodiment, so descriptions thereof are omitted. You may combine 2nd Embodiment and 3rd Embodiment.
[0051]

Next, a face authentication environment determination method according to the third embodiment will be described with reference to FIG. FIG. 8 is a flowchart showing a face authentication environment determination method according to the third embodiment. In the description of FIG. 8, FIG. 6 and FIG. 7 will be referred to as appropriate.
The face authentication environment determination method according to the present embodiment includes step ST2a instead of step ST2 shown in FIG. 4, and further includes step ST11.
[0052]
First, as shown in FIG. 8, the camera 20 takes an image of the skin color chart 10 in which the first skin color display portion BK, the second skin color display portion WT, and the gray display portion GR are formed on the substrate 11 (step ST1). ).
Next, the image analysis unit 110 analyzes the brightness of the gray display portion GR in addition to the brightness of the first skin color display portion BK and the second skin color display portion WT in the captured image of the skin color chart (step ST2a). ).
[0053]
Next, the dynamic range determination section 130 determines whether or not the dynamic range of the camera 20 is appropriate based on the brightness of the gray display portion GR (step ST11). If the dynamic range of the camera 20 is inappropriate (step ST11 NO), the determination ends. On the other hand, if the dynamic range of the camera 20 is appropriate (step ST11 YES), the environment determination unit 120 determines that the imaging environment of the image is face authentication based on the luminance of the first skin color display unit BK and the second skin color display unit WT. (step ST3). Since step ST3 and subsequent steps are the same as those of the face authentication environment determination method according to the first embodiment shown in FIG. 4, description thereof is omitted.
[0054]
As described above, the face authentication environment determination method according to the third embodiment determines the dynamic range before determining the face authentication environment. Then, the face authentication environment is determined only when the dynamic range is appropriate. Therefore, the face authentication environment can be determined more appropriately than the face authentication environment determination method according to the first embodiment.
[0055]
(Fourth embodiment)
Next, a skin color chart in the face authentication environment determination system according to the fourth embodiment will be described with reference to FIG. FIG. 9 is a plan view showing a skin color chart in the face authentication environment determination system according to the fourth embodiment.
The skin color chart 10 shown in FIG. 9 includes a third skin color display section YL in addition to the skin color chart 10 shown in FIG.
[0056]
As shown in FIG. 9, the third skin color display portion YL is also formed on the substrate 11 in the same manner as the first skin color display portion BK and the second skin color display portion WT. Although the arrangement position of the third skin color display portion YL is not particularly limited, in the example shown in FIG. 9, the third skin color display portion YL is positioned between the first skin color display portion BK and the second skin color display portion WT. is provided.
[0057]
The third skin color display portion YL represents a skin color between the skin color in the first skin color display portion BK and the skin color in the second skin color display portion WT. The third skin color display portion YL indicates, for example, a standard yellow (Mongoloid) skin color. Specifically, the lightness L* of the skin color in the third skin color display portion YL expressed in the CIE L*a*b* color space satisfies, for example, 62≦L*≦68. Also, the chromaticities a* and b* of the third skin color display portion YL satisfy, for example, a*=11 and 18≦b*≦19.
[0058]
By providing the third skin color display unit YL, when determining the face authentication environment, the environment can be evaluated in more detail than in the first to third embodiments. Specifically, the environment in which the third skin color display portion YL, in addition to the first skin color display portion BK, also suffers from the black loss is darker than the environment in which the black loss occurs only in the first skin color display portion BK. I understand. Also, it can be seen that the environment in which overexposure occurs not only in the second skin color display portion WT but also in the third skin color display portion YL is brighter than the environment in which overexposure occurs only in the second skin color display portion WT. . Based on such an evaluation, it becomes easy to adjust, for example, the installation position and orientation of the camera, the brightness of the location where the image is taken, and the like.
[0059]
In the example shown in FIG. 9, the third skin color display portion YL has a square planar shape, but is not limited in any way.
Other configurations are the same as in the third embodiment, so descriptions thereof are omitted. You may combine 2nd Embodiment and 4th Embodiment. Also, in the fourth embodiment, the grayscale portions GS1 and GS2 may not be formed. In other words, the third skin color display section YL may be added to the skin color chart 10 shown in FIG.
[0060]
(Fifth embodiment)
Next, with reference to FIG. 10, a skin color chart in the face authentication environment determination system according to the fifth embodiment will be described. FIG. 10 is a plan view showing a skin color chart in the face authentication environment determination system according to the fifth embodiment.
The skin color chart 10 shown in FIG. 10 includes a fourth skin color display section 14 and a fifth skin color display section 15 in addition to the skin color chart 10 shown in FIG.
[0061]
As shown in FIG. 10 , the fourth skin color display portion 14 and the fifth skin color display portion 15 are also formed on the substrate 11 . Although the arrangement positions of the fourth skin color display portion 14 and the fifth skin color display portion 15 are not particularly limited, in the example shown in FIG. 3 and the flesh color display portion YL. The fifth skin color display portion 15 is provided between the second skin color display portion WT and the third skin color display portion YL.
[0062]
The fourth skin color display portion 14 represents a skin color between the skin color in the first skin color display portion BK and the skin color in the third skin color display portion YL.
The fifth skin color display portion 15 represents a skin color between the skin color in the second skin color display portion WT and the skin color in the third skin color display portion YL.
[0063]
By providing the fourth skin color display unit 14, when determining the face authentication environment, the environment can be evaluated in more detail than in the fourth embodiment. Specifically, it is possible to distinguish between an environment in which the first skin-color display portion BK and the fourth skin-color display portion 14 are underexposed black and an environment in which only the first skin-color display portion BK is underexposed to black. Furthermore, an environment in which black crushing occurs in the first skin color display portion BK, the fourth skin color display portion 14, and the third skin color display portion YL, and the first skin color display portion BK and the fourth skin color display portion 14 It can be distinguished from an environment in which black crushing only occurs.
[0064]
Similarly, by providing the fifth skin color display unit 15, when determining the face authentication environment, the environment can be evaluated in more detail than in the fourth embodiment. Specifically, it is possible to distinguish between an environment in which overexposure occurs in the second skin color display portion WT and the fifth skin color display portion 15 and an environment in which overexposure occurs only in the second skin color display portion WT. Furthermore, the second skin color display portion WT, the fifth skin color display portion 15, and the third skin color display portion YL have an environment in which overexposure occurs, and the second skin color display portion WT and the fifth skin color display portion 15 It is possible to distinguish from an environment in which overexposure only occurs.
Based on such an evaluation, it becomes easier to adjust, for example, the installation position and orientation of the camera, and the brightness of the location where the image is taken.
[0065]
In the example shown in FIG. 10, the fourth skin color display portion 14 and the fifth skin color display portion 15 have a square planar shape, but are not limited in any way. Also, the skin color chart 10 may include only one of the fourth skin color display portion 14 and the fifth skin color display portion 15 .
Further, the skin color chart 10 may be provided with a plurality of fourth skin color display sections 14 that indicate different skin colors. Similarly, the skin color chart 10 may be provided with a plurality of fifth skin color display sections 15 showing different skin colors.
Further, in the present embodiment, the skin colors in the third skin color display section YL, the fourth skin color display section 14, and the fifth skin color display section 15 indicate, for example, the average skin color in a specific country or region. good too.
[0066]
Other configurations are the same as those of the fourth embodiment, so descriptions thereof are omitted. You may combine 2nd Embodiment and 5th Embodiment. Also, in the fifth embodiment, the grayscale portions GS1 and GS2 may not be formed. That is, a third skin color display section YL, a fourth skin color display section 14, and a fifth skin color display section 15 may be added to the skin color chart 10 shown in FIG.
[0067]
Each functional block in the above-described embodiments is configured by hardware or software, or both, and may be configured by one piece of hardware or software, or may be configured by multiple pieces of hardware or software. The function (processing) of each device may be realized by a computer having a CPU (Central Processing Unit), memory, and the like. For example, a computer program for performing the method in the embodiment may be stored in a storage device, and each function may be realized by executing the computer program stored in the storage device with a CPU.
[0068]
These computer programs can be stored and supplied to computers using various types of non-transitory computer readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (eg, flexible discs, magnetic tapes, hard disk drives), magneto-optical recording media (eg, magneto-optical discs), CD-ROMs (Read Only Memory), CD-Rs, CD-R/W, semiconductor memory (eg, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)). Computer programs may also be delivered to computers on various types of transitory computer readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can deliver the computer program to the computer via wired channels, such as wires and optical fibers, or wireless channels.
[0069]
Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.
[0070]
Some or all of the above embodiments can also be described as the following additional remarks, but are not limited to the following.
(Appendix 1)
A skin color chart in which a first skin color display unit representing a Negroid skin color and a second skin color display unit representing a Caucasian skin color are formed on a substrate is imaged,
Analyzing the brightness of the first and second skin color display parts in the captured image of the skin color chart,
Determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units,
Face authentication environment determination method.
(Appendix 2)
A plurality of gray display parts with different reflectances are formed on the substrate of the skin color chart,
When analyzing the brightness of the first and second skin color display parts, the brightness of the plurality of gray display parts is also analyzed,
Determining whether the dynamic range of the imaging means that captured the image is appropriate based on the brightness of the plurality of gray display parts,
Determining whether the imaging environment of the image is suitable for face authentication when the dynamic range is appropriate,
The face authentication environment determination method according to appendix 1.
(Appendix 3)
the lightness L* of the first skin color display portion in the CIE L*a*b* color space satisfies 20≦L*≦37,
the lightness L* of the second skin color display portion in the CIE L*a*b* color space satisfies 74≦L*≦81,
The face authentication environment determination method according to appendix 1 or 2.

The scope of the claims
[Claim 1]
A skin color chart in which a first skin color display unit representing a Negroid skin color and a second skin color display unit representing a Caucasian skin color are formed on a substrate is imaged,
Analyzing the brightness of the first and second skin color display parts in the captured image of the skin color chart,
Determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units,
Face authentication environment determination method.
[Claim 2]
A plurality of gray display parts with different reflectances are formed on the substrate of the skin color chart,
When analyzing the brightness of the first and second skin color display parts, the brightness of the plurality of gray display parts is also analyzed,
Determining whether the dynamic range of the imaging means that captured the image is appropriate based on the brightness of the plurality of gray display parts,
Determining whether the imaging environment of the image is suitable for face authentication when the dynamic range is appropriate,
The face authentication environment determination method according to claim 1.
[Claim 3]
the lightness L* of the first skin color display portion in the CIE L*a*b* color space satisfies 20≦L*≦37,
the lightness L* of the second skin color display portion in the CIE L*a*b* color space satisfies 74≦L*≦81,
The face authentication environment determination method according to claim 1 or 2.
[Claim 4]
The first and second skin color display parts are formed in a three-dimensional shape imitating a human face,
The face authentication environment determination method according to any one of claims 1 to 3.
[Claim 5]
The skin color chart further comprises a third skin color display section that represents a skin color between the skin color in the first skin color display section and the skin color in the second skin color display section,
the lightness L* of the third skin color display portion in the CIE L*a*b* color space satisfies 62≦L*≦68,
The face authentication environment determination method according to any one of claims 1 to 4.
[Claim 6]
a fourth skin color display section representing a skin color between the skin color in the first skin color display section and the skin color in the third skin color display section;
The skin color chart further includes at least one of: a fifth skin color display section representing a skin color between the skin color in the second skin color display section and the skin color in the third skin color display section;
The face authentication environment determination method according to claim 5.
[Claim 7]
the substrate is black,
The face authentication environment determination method according to any one of claims 1 to 6.
[Claim 8]
a skin color chart formed on a substrate with a first skin color display portion representing a negroid skin color and a second skin color display portion representing a caucasian skin color;
an imaging means for imaging the skin color chart;
an image analysis means for analyzing the brightness of the first and second skin color display parts in the image of the skin color chart captured by the imaging means;
environment determination means for determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units;
Face recognition environment determination system.
[Claim 9]
A plurality of gray display parts with different reflectances are formed on the substrate of the skin color chart,
The image analysis means analyzes the brightness of the plurality of gray display parts,
The face authentication environment determination system further comprises dynamic range determination means for determining whether or not the dynamic range of the imaging means is appropriate based on the brightness of the plurality of gray display parts,
The face authentication environment determination system according to claim 8.
[Claim 10]
the lightness L* of the first skin color display portion in the CIE L*a*b* color space satisfies 20≦L*≦37,
the lightness L* of the second skin color display portion in the CIE L*a*b* color space satisfies 74≦L*≦81,
The face authentication environment determination system according to claim 8 or 9.
[Claim 11]
The first and second skin color display parts are formed in a three-dimensional shape imitating a human face,
The face authentication environment determination system according to any one of claims 8 to 10.
[Claim 12]
The skin color chart further comprises a third skin color display section that represents a skin color between the skin color in the first skin color display section and the skin color in the second skin color display section,
the lightness L* of the third skin color display portion in the CIE L*a*b* color space satisfies 62≦L*≦68,
The face authentication environment determination system according to any one of claims 8 to 11.
[Claim 13]
a fourth skin color display section representing a skin color between the skin color in the first skin color display section and the skin color in the third skin color display section;
The skin color chart further includes at least one of: a fifth skin color display section representing a skin color between the skin color in the second skin color display section and the skin color in the third skin color display section;
The face authentication environment determination system according to claim 12.
[Claim 14]
the substrate is black,
The face authentication environment determination system according to any one of claims 8 to 13.
[Claim 15]
Analyzing the brightness of the first and second skin color display portions in the image of the skin color chart in which the first skin color display portion representing the Negroid skin color and the second skin color display portion representing the Caucasian skin color are formed on a substrate. an image analysis means for
environment determination means for determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units;
Face authentication environment determination device.
[Claim 16]
A plurality of gray display parts with different reflectances are formed on the substrate of the skin color chart.,
The image analysis means also analyzes the brightness of the plurality of gray display parts,
further comprising dynamic range determination means for determining whether or not the dynamic range of the imaging means that captured the image is appropriate, based on the brightness of the plurality of gray display parts;
The face authentication environment determination device according to claim 15.
[Claim 17]
Analyzing the brightness of the first and second skin color display portions in the image of the skin color chart in which the first skin color display portion representing the Negroid skin color and the second skin color display portion representing the Caucasian skin color are formed on a substrate. death,
Determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units,
　Stores a face recognition environment determination program that causes the computer to execute the process,
A non-transitory computer-readable medium.
[Claim 18]
A plurality of gray display parts with different reflectances are formed on the substrate of the skin color chart,
When analyzing the brightness of the first and second skin color display parts, the brightness of the plurality of gray display parts is also analyzed,
Determining whether the dynamic range of the imaging means that captured the image is appropriate based on the brightness of the plurality of gray display parts,
Determining whether the imaging environment of the image is suitable for face authentication when the dynamic range is appropriate,
18. The non-transitory computer-readable medium of claim 17.
[Claim 19]
Analyzing the brightness of the first and second skin color display portions in the image of the skin color chart in which the first skin color display portion representing the Negroid skin color and the second skin color display portion representing the Caucasian skin color are formed on a substrate. death,
Determining whether the imaging environment of the image is suitable for face authentication based on the luminance of the first and second skin color display units,
Face authentication environment determination method.
[Claim 20]
A plurality of gray display parts with different reflectances are formed on the substrate of the skin color chart,
When analyzing the brightness of the first and second skin color display parts, the brightness of the plurality of gray display parts is also analyzed,
Determining whether the dynamic range of the imaging means that captured the image is appropriate based on the brightness of the plurality of gray display parts,
Determining whether the imaging environment of the image is suitable for face authentication when the dynamic range is appropriate,
The face authentication environment determination method according to claim 19.