Program product, evaluation device, and method
By using computer processing and the brightness characteristics of MediaPipe landmark locations, the glossy area of the cheek can be easily estimated, solving the problem of the difficulty in determining the location of the glossy area of the cheek, and realizing the simple evaluation and prediction of the glossy area.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-16
- Publication Date
- 2026-03-31
AI Technical Summary
Due to the complex surface shape of the cheek, it is difficult to determine the location of the cheek's luster by measuring the reflected light.
The program product enables the computer to perform processing to obtain facial data of the subject and estimate the glossy area of the cheek when viewed from a specific angle. The state of the glossy area is evaluated using the landmark location and brightness characteristics of MediaPipe.
It can easily estimate the location of luster on the cheeks, evaluate the presence or absence of luster areas, the type and degree of luster, and predict changes in luster areas.
Smart Images
Figure CN121768053A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to program products, evaluation devices, and methods. Background Technology
[0002] Previously, it was known that beautiful skin would have a dewy glow on the higher parts of the cheeks. For example, it could be assumed that if a customer or beautician could identify the location of the glow on a customer's cheeks, they could choose appropriate cosmetics. Summary of the Invention
[0003] <Problem to be solved by this invention>
[0004] However, due to the complex shape of the cheek surface, it is not easy to determine the location of the cheek's luster by measuring the reflected light.
[0005] Therefore, the purpose of this invention is to easily estimate the location of the luster on the cheeks.
[0006] <Methods for solving problems>
[0007] An embodiment of the present invention includes a program for causing a computer to perform the following processing: acquiring data representing at least the cheeks of an object; estimating, when viewed from any position from the front of the object 90 degrees to the right and 90 degrees to the left, all areas of the cheeks of the object seen in close proximity, where the direction vector from the center point of the object's head through the cheek surface toward the observer coincides with the normal vector of the cheek surface.
[0008] <The Effects of the Invention>
[0009] According to the present invention, the location of the luster on the cheeks can be easily estimated. Attached Figure Description
[0010] Figure 1 This is a diagram used to illustrate the general outline of the present invention.
[0011] Figure 2 This is an example of the overall structure involved in one embodiment of the present invention.
[0012] Figure 3 This is a functional structure diagram of an evaluation device according to one embodiment of the present invention.
[0013] Figure 4 This is a diagram used to illustrate a MediaPipe according to an embodiment of the present invention.
[0014] Figure 5 This is a diagram illustrating the determination result of whether the landmark of the MediaPipe according to an embodiment of the present invention is included in the glossy area.
[0015] Figure 6 This is a diagram illustrating the change of the glossy region with age according to one embodiment of the present invention.
[0016] Figure 7 This is a diagram used to illustrate glossy skin, reflective skin, and matte skin according to one embodiment of the present invention.
[0017] Figure 8 This is a diagram used to illustrate the beautiful gloss and distorted gloss according to one embodiment of the present invention.
[0018] Figure 9 This is a flowchart of the presumption process according to one embodiment of the present invention.
[0019] Figure 10 This is a hardware structure diagram of a server device and a client device according to an embodiment of the present invention. Detailed Implementation
[0020] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.
[0021] <Outline>
[0022] Figure 1 This is a diagram used to illustrate the general outline of the present invention. In one embodiment of the present invention, it is possible to estimate the area (glossy area) that may produce shine on the cheeks and evaluate the state of the glossy area.
[0023] The "glossy area" is the area where the cheek may produce a glossy appearance. Specifically, the glossy area is the entire area of the cheek seen from the front of the subject when viewed from any position from 90 degrees to the right to 90 degrees to the left, where the direction vector from the center of the subject's head (specifically, the center when approximating the skull as a sphere) through the cheek surface toward the observer (virtual observer) is consistent with the normal vector of the cheek surface. (Furthermore, the phrase "the direction vector from the center of the subject's head through the cheek surface toward the observer is consistent with the normal vector of the cheek surface" is not limited to the case where the angle between the two vectors is 0 degrees or 180 degrees, but also includes the case where the angle between the two vectors is less than a predetermined threshold (i.e., the direction of the two vectors has a slight difference)). More specifically, the glossy area is the region on the cheek where the normal vector of the cheek surface points diagonally to the right (horizontal plane and 45 degrees to the right from the front of the face) if it is the right cheek, and diagonally to the left (horizontal plane and 45 degrees to the left from the front of the face) if it is the left cheek.
[0024] In one embodiment of the present invention, the location of landmarks 50 and / or 280 of the MediaPipe contained within the glossy area can be determined to evaluate the glossy area. For example, in one embodiment of the present invention, the location of the glossy area can be evaluated, whether the glossy area is glossy or matte, whether the glossy area is glossy or reflective, and whether the gloss of the glossy area is a beautiful gloss or a distorted gloss.
[0025] <Example of an overall structure>
[0026] Figure 2 This is an example of the overall structure involved in one embodiment of the present invention.
[0027] [Structure Example 1]
[0028] The evaluation system 1 includes a server device 10 and a client device 20. These will be described separately below.
[0029] <<Server Device>>
[0030] Server device 10 is a device for estimating the glossy area of the cheek of subject 30. Server device 10 consists of one or more computers.
[0031] Specifically, server device 10 acquires data representing the cheeks of subject 30 and estimates the glossy areas of subject 30's cheeks (specifically, when viewed from any position from 90 degrees to the right or left of the subject 30's front, the area of the cheeks seen in close proximity that has a direction vector from the center point of the subject 30's head through the cheek surface toward the observer that coincides with the normal vector of the cheek surface). For example, server device 10 receives data representing the cheeks of subject 30 from client device 20 and sends the estimated results of the glossy areas of subject 30's cheeks to client device 20.
[0032] <<Client Device>>
[0033] The client device 20 sends data representing the cheeks of the subject 30 to the server device 10, and receives and displays estimation results of the glossy areas of the subject 30's cheeks from the server device 10. Additionally, the client device 20 may also perform a portion of the processing described in this specification by the server device 10. For example, the client device 20 may be a personal computer, tablet terminal, smartphone, etc. The client device 20 may also include a camera unit.
[0034] [Structure Example 2]
[0035] In structural example 2, the glossy area of the subject's cheek is estimated by the client device 20, not the server device 10. Specifically, the client device 20 acquires data representing the subject's cheek and estimates the glossy area of the subject's cheek (specifically, when viewed from any position from 90 degrees to the right or left of the subject's front, all areas of the subject's cheek seen in close proximity, where the direction vector from the center point of the subject's head through the cheek surface toward the observer coincides with the normal vector of the cheek surface). The client device 20 can be a personal computer, tablet terminal, smartphone, etc. The client device 20 may also include a camera unit.
[0036] <Functional Composition>
[0037] Figure 3 This is a functional structure diagram of the evaluation devices 10 and 20 according to one embodiment of the present invention.
[0038] The evaluation devices 10 and 20 may include a cheek data acquisition unit 101, an estimation unit 102, an evaluation unit 103, and a prompting unit 104. By executing a program, the evaluation devices 10 and 20 can function as the cheek data acquisition unit 101, the estimation unit 102, the evaluation unit 103, and the prompting unit 104.
[0039] The cheek data acquisition unit 101 acquires data representing at least the cheeks of the subject 30. For example, the data representing at least the cheeks of the subject 30 is an image (two-dimensional image) obtained by taking a picture of at least the cheeks of the subject 30. Alternatively, the data representing at least the cheeks of the subject 30 may also be point cloud data representing a three-dimensional shape.
[0040] The estimation unit 102 estimates the glossy area of the subject 30's cheek (i.e., when viewed from any position from 90 degrees to the right or left of the subject 30's front, all areas of the subject 30's cheek that are visible in close proximity, where the direction vector from the center point of the subject 30's head through the cheek surface toward the observer coincides with the normal vector of the cheek surface). Alternatively, in one embodiment of the invention, the evaluation devices 10 and 20 may also distinguish between glossy areas and areas other than glossy areas within the data representing at least the cheeks of the subject 30, and extract and display the glossy areas (or areas other than glossy areas).
[0041] For example, the estimation unit 102 estimates the glossy area of the subject 30's cheeks through image analysis, or it estimates the glossy area of the subject 30's cheeks using a learned model.
[0042] For example, evaluation devices 10 and 20 store learned models generated by any device (learning device), and use these learned models to estimate the glossy areas of the cheeks of subject 30. The learning device generates teacher data (i.e., "data representing at least the cheeks" and "glossy areas" collected from multiple individuals) as input to "data representing at least the cheeks" (e.g., images of at least the cheeks taken) and output to "glossy areas". The learning device uses this teacher data to learn, thereby reducing the difference between the output of the model when the "data representing at least the cheeks" (as teacher data) is input and the "glossy areas" (as teacher data), to generate the learned model.
[0043] For example, the estimation unit 102 uses images of at least the cheek of the subject 30 to determine the location of the subject 30's MediaPipe 50 and / or 280 landmarks.
[0044] The evaluation unit 103 evaluates the condition of the subject 30’s skin based on the brightness of the image of at least the cheek of the subject 30 captured (specifically, the brightness of the location determined by the estimation unit 102 (the location of the landmark at MediaPipe No. 50 and / or No. 280 of the subject 30).
[0045] [Evaluation of the presence or absence of luster]
[0046] For example, when the average brightness of the surrounding area including the location determined by estimation unit 102 (the location of landmarks 50 and / or 280 of the MediaPipe of the object 30) is high (e.g., above a threshold) and the brightness uniformity is high (e.g., above a threshold), the evaluation unit 103 evaluates the glossy area as glossy. On the other hand, when the difference between the average brightness of the surrounding area including the location determined by estimation unit 102 (the location of landmarks 50 and / or 280 of the MediaPipe of the object 30) and the average brightness of the area outside the surrounding area is small (e.g., below a threshold), the evaluation unit 103 evaluates the glossy area as non-glossy.
[0047] [Evaluation of gloss and reflectivity]
[0048] For example, when the average brightness of the surrounding area including the location determined by estimation unit 102 (the location of landmarks 50 and / or 280 of the MediaPipe of the object 30) is high (e.g., above a threshold) and the brightness uniformity is high (e.g., above a threshold), the evaluation unit 103 evaluates the glossy area as glossy. For example, when the average brightness of the surrounding area including the location determined by estimation unit 102 (the location of landmarks 50 and / or 280 of the MediaPipe of the object 30) is high (e.g., above a threshold) and the brightness uniformity is low (e.g., below a threshold), the evaluation unit 103 evaluates the glossy area as reflective. Furthermore, refer to the following... Figure 7 Let me elaborate.
[0049] Furthermore, the peripheral area in the aforementioned [evaluation of the presence or absence of gloss] and [evaluation of gloss and reflection] can be the same area as the glossy area of the cheek (i.e., when viewed from any position from the front of the subject 30 at 90 degrees to the right to 90 degrees to the left, all areas of the cheek of the subject 30 seen in close proximity, in which the direction vector from the center point of the subject 30's head through the cheek surface toward the observer coincides with the normal vector of the cheek surface), or it can be a different area.
[0050] [Evaluation of beautiful shine and distorted shine]
[0051] For example, when the brightness of the upper semicircle of a circle centered on the position determined by estimation unit 102 (the position of landmarks 50 and / or 280 of the MediaPipe of the object 30) is the same as the brightness of the lower semicircle of the circle, or when the brightness of the upper semicircle of the circle is higher than the brightness of the lower semicircle of the circle, the evaluation unit 103 evaluates the gloss of the gloss area as beautiful gloss. For example, when the brightness of the lower semicircle of a circle centered on the position determined by estimation unit 102 (the position of landmarks 50 and / or 280 of the MediaPipe of the object 30) is higher than the brightness of the upper semicircle of the circle, the evaluation unit 103 evaluates the gloss of the gloss area as distorted gloss. Further details will be provided later. Figure 8 Let me elaborate.
[0052] Additionally, the circle in the above-mentioned [evaluation of beautiful gloss and distorted gloss] can also be the same area as the glossy area of the cheek (i.e., when viewed from any position from the front of the subject 30 at 90 degrees to the right to 90 degrees to the left, in the cheek area seen in front, the direction vector from the center point of the subject 30's head through the cheek surface toward the observer is consistent with the normal vector of the cheek surface) (i.e., the glossy area consists of an upper semicircle area and a lower semicircle area).
[0053] The evaluation unit 103 evaluates the changes in the position (the position of the MediaPipe 50 and / or 280 landmarks of the subject 30) caused by relaxation based on the position determined by the estimation unit 102 (the position of the MediaPipe 50 and / or 280 landmarks of the subject 30) and the outer corner of the subject 30's eye (i.e., the position of the outer corner of the eye in the data representing at least the cheek of the subject 30). Specifically, the evaluation unit 103 can predict the position of the glossy area 20 years later (i.e., the position of the MediaPipe 50 and / or 280 landmarks 20 years later) after extending the vector from the position of the outer corner of the eye as the starting point and the position determined by the estimation unit 102 (the position of the MediaPipe 50 and / or 280 landmarks of the subject 30) to a value corresponding to "(the subject 30's actual age - 20) × 4 mm".
[0054] The prompting unit 104 prompts the results estimated by the estimation unit 102 and the results evaluated by the evaluation unit 103.
[0055] For example, the prompting unit 104 displays the location determined by the estimation unit 102 (the location of the MediaPipe landmarks 50 and / or 280 of the subject 30) on the data representing at least the cheeks of the subject 30. Furthermore, the prompting unit 104 displays, in a comparable manner, the location determined by the estimation unit 102 (the location of the MediaPipe landmarks 50 and / or 280 of the subject 30) and the average of that location for people of the same age as the subject 30. Additionally, the prompting unit 104 displays the location of the glossy area 20 years from now (i.e., the location of the MediaPipe landmarks 50 and / or 280 in 20 years from now). Furthermore, the prompting unit 104 displays beauty-related information (cosmetics and other products, beauty methods, equipment, etc.) corresponding to the results estimated by the estimation unit 102.
[0056] [Characteristics of the cheek]
[0057] Figure 4 This is a diagram used to illustrate a MediaPipe according to an embodiment of the present invention. In one embodiment of the present invention, the MediaPipe as shown in the reference diagram is flexibly utilized. Figure 5As described in detail, MediaPipe landmarks 50 and 280 are included in the glossy area. As representative points of the glossy area, at least one of MediaPipe landmarks 50 and 280 can be used. MediaPipe is a function that detects the positions of landmarks (feature points) within a face from an image captured of the face. Furthermore, while this specification describes a method using MediaPipe, it is not limited to this. In this invention, any method for extracting feature points of an object (feature points included in the glossy area of the cheek) through object detection can be used.
[0058] Figure 5 This diagram illustrates the determination results of whether a landmark of the MediaPipe according to an embodiment of the present invention is included in the glossy area. The determination was made for whether landmark number 280 of the MediaPipe, for subjects aged 20 to 70, was included in the glossy area (i.e., all areas of the cheek of the subject 30, viewed from any position from the front of the subject 30 at 90 degrees to the right and 90 degrees to the left, where the direction vector from the center point of the subject 30's head through the cheek surface toward the observer coincides with the normal vector of the cheek surface). Of the 129 subjects, 21 had no glossy area and could not be determined, and 17 could not be determined due to the inability to detect faces.
[0059] • Of those in their 20s, 15 are MediaPipe 280 landmarks included in the Glossy area, 3 are not included, and 2 are undetermined.
[0060] • Of those in their 30s, 15 are MediaPipe’s landmark number 280, which is included in the Glossy area; 1 is not included; and 4 are undetermined.
[0061] • Of those in their 40s, 14 are MediaPipe 280 landmarks included in the Glossy area, 2 are not included, and 7 are undetermined.
[0062] • Of those in their 50s, 20 are MediaPipe Landmark 280 and are included in the Glossy area, 1 is not included, and 1 is undetermined.
[0063] • Of those in their 60s, 11 are MediaPipe’s landmark number 280, which is included in the Glossy area; 1 is not included; and 9 are undetermined.
[0064] • Of those in their 70s, 16 are MediaPipe Landmark 280 within the Glossy area, 1 is not included, and 6 are undetermined.
[0065] • Of the individuals aged 20 to 70, 91 were located at MediaPipe No. 280 and were included in the Glitter area, 9 were not included, and 29 were undetermined.
[0066] In 90% of the subjects who could be identified, landmark number 280 of MediaPipe was included in the glossy area. Moreover, there was no age-related bias. Therefore, it is not problematic to consider landmark number 280 of MediaPipe (and consequently, landmark number 50 of the opposite cheek) as a representative point of the glossy area.
[0067] [Changes in glossy areas]
[0068] Figure 6 This is a diagram illustrating the changes in the glossy region caused by age according to an embodiment of the present invention.
[0069] Figure 6 The distribution of the "<20s-30s>" shows the average location of the center of the glossy area in people in their 20s-30s, 40s-50s, and 60s-70s. Furthermore, Figure 6 The distribution of the luster area in people aged 20 to 30 shows the distribution of the central location of the luster area in people aged 20 to 30.
[0070] Figure 6 The distribution of the "<60s-70s>" shows the average location of the center of the glossy area in people in their 20s-30s, 40s-50s, and 60s-70s. Furthermore, Figure 6 The distribution of the luster area in people aged 60 to 70 shows the distribution of the central location of the luster area in people aged 60 to 70.
[0071] like Figure 6 As shown, with age, the center of the glossy area shifts downwards (3-4 mm over 15-20 years) and spreads across the entire cheek. Based on this change in the center of the glossy area, the future locations of MediaPipe landmarks 50 and / or 280 can be predicted.
[0072] [Presence or absence of gloss, evaluation of gloss and reflection]
[0073] Figure 7 This diagram illustrates glossy skin, reflective skin, and matte skin according to one embodiment of the present invention. The vertical axis represents the intensity (brightness) of the skin's gloss (spectral reflection), and the horizontal axis represents the uniformity of the skin's gloss (spectral reflection). Figure 7 As shown, in glossy skin, the intensity (brightness) of the gloss (spectral reflection) is moderate and the reflection is uniform. Conversely, in reflective skin, the intensity (brightness) of the gloss (spectral reflection) is excessively high and the reflection is uneven (due to factors such as pores). Furthermore, in matte skin, the intensity (brightness) of the gloss (spectral reflection) is low. Based on these characteristics of glossy, reflective, and matte skin, areas with a glossy appearance can be evaluated.
[0074] [Evaluation of beautiful shine and distorted shine]
[0075] Figure 8 This is a diagram used to illustrate the beautiful gloss and distorted gloss according to one embodiment of the present invention.
[0076] For example, such as Figure 8 As shown in the <Beautiful Gloss> section, when the brightness of the upper half of the circle centered on the position determined by the estimation unit 102 (the position of the MediaPipe No. 50 and / or No. 280 of the object 30) is the same as the brightness of the lower half of the circle, or the brightness of the upper half of the circle is higher than the brightness of the lower half of the circle, the evaluation unit 103 evaluates the luster of the luster area as a beautiful luster (or a youthful luster).
[0077] For example, such as Figure 8 As shown in the <Distorted Gloss>, when the brightness of the lower half of the circle centered on the position determined by the estimation unit 102 (the position of the MediaPipe of the object 30 at number 50 and / or number 280) is higher than the brightness of the upper half of the circle, the evaluation unit 103 evaluates the gloss of the gloss area as distorted gloss.
[0078] Additionally, the upper semicircular region is the frontal region of a circle (or ellipse) centered on the position determined by the presumption 102 (the position of landmarks 50 and / or 280 of the MediaPipe of the subject 30). Furthermore, the lower semicircular region is the palatal region of a circle (or ellipse) centered on the position determined by the presumption 102 (the position of landmarks 50 and / or 280 of the MediaPipe of the subject 30).
[0079] <Method>
[0080] Figure 9 This is a flowchart of the gloss region estimation process according to one embodiment of the present invention.
[0081] In step 1 (S1), the cheek data acquisition unit 101 acquires data representing at least the cheeks of the subject 30 (for example, by capturing an image of at least the cheeks of the subject 30).
[0082] In step 2 (S2), the estimation unit 102 uses the data obtained in S1 to estimate the glossy area of the subject 30's cheek (i.e., when viewed from any position from 90 degrees to the right or 90 degrees to the left from the front of the subject 30, all areas of the subject 30's cheek that are in close proximity to the observer, where the direction vector from the center point of the subject 30's head through the cheek surface toward the observer coincides with the normal vector of the cheek surface).
[0083] In step 3 (S3), the prompting unit 104 prompts the result estimated in S2 (for example, displaying the glossy area of the cheek of the subject 30 on the data representing at least the cheek of the subject 30).
[0084] <Effect>
[0085] Thus, in one embodiment of the present invention, the location of the cheek's shine can be easily estimated, making it easy to compare with the location of the cheek's shine in people of the same age group or to predict changes in the location of the subject's cheek's shine. Furthermore, in one embodiment of the present invention, by evaluating whether the shine area of the cheek has shine, whether it is shiny or reflective, or whether the shine is beautiful or distorted, a comprehensive evaluation can be performed.
[0086] <Hardware Structure>
[0087] Figure 10 This is a hardware structure diagram of a server device 10 and a client device 20 according to an embodiment of the present invention. The server device 10 and the client device 20 may include a control unit 1001, a main storage unit 1002, an auxiliary storage unit 1003, an input unit 1004, an output unit 1005, and an interface unit 1006. These will be described separately below.
[0088] The control unit 1001 is a processor (such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), etc.) that executes various programs installed in the auxiliary storage unit 1003.
[0089] The main storage unit 1002 includes non-volatile memory (ROM (Read Only Memory)) and volatile memory (RAM (Random Access Memory)). The ROM stores various programs, data, etc., required by the control unit 1001 to execute various programs installed in the auxiliary storage unit 1003. The RAM provides the operating area when the control unit 1001 executes various programs installed in the auxiliary storage unit 1003.
[0090] The auxiliary storage unit 1003 is an auxiliary storage device that stores various programs and information used when executing those programs.
[0091] The input unit 1004 is an input device for the operator of the server device 10 and the client device 20 to input various instructions to the server device 10 and the client device 20.
[0092] The output unit 1005 is an output device that outputs the internal status of the server device 10 and the client device 20.
[0093] Interface unit 1006 is a communication device used for connecting to a network and communicating with other devices.
[0094] The embodiments of the present invention have been described in detail above, but the present invention is not limited to the specific embodiments described above. Various modifications and alterations can be made within the scope of the spirit of the present invention as set forth in the claims.
[0095] Label Explanation
[0096] 1: Evaluation System
[0097] 10: Server equipment
[0098] 20: Client device
[0099] 30: The Object
[0100] 101: Cheek Data Acquisition Department
[0101] 102: Presumption Department
[0102] 103: Evaluation Department
[0103] 104: Reminder Department
[0104] 1001: Control Department
[0105] 1002: Main Storage Unit
[0106] 1003: Auxiliary Storage Unit
[0107] 1004: Input Section
[0108] 1005: Output Department
[0109] 1006: Interface Section.
Claims
1. A program product including a program that causes a computer to execute the following processing: acquire data representing at least a cheek of a subject; and estimate, when viewed at any position from a front of the subject to 90 degrees right to 90 degrees left, all regions of the cheek of the subject in which a direction vector from a center point of the head of the subject through a cheek surface toward an observer is aligned with a normal vector of the cheek surface in a cheek portion seen in the near distance.
2. The program product according to claim 1, wherein the estimation is estimation by image analysis or estimation using a learned model.
3. The program product according to claim 1, wherein the estimation is determination of positions of landmarks of No. 50 and / or No. 280 of MediaPipe of the subject.
4. The program product according to claim 3, wherein the program causes the computer to further execute the following processing: display the determined positions on the data representing at least the cheek of the subject.
5. The program product according to claim 3, wherein the program causes the computer to further execute the following processing: display the determined positions and an average of the positions of people of the same age group as the subject in a comparable manner.
6. The program product according to claim 3, wherein the data representing at least the cheek of the subject is a two-dimensional image obtained by photographing at least the cheek of the subject.
7. The program product according to claim 6, wherein the program causes the computer to further execute the following processing: evaluate a state of the skin of the subject based on luminance of the determined positions of the two-dimensional image.
8. The program product according to claim 7, wherein with respect to the evaluation, when a difference between an average of luminance of a peripheral region including the determined positions and an average of luminance of a region other than the peripheral region is small, the evaluation is no gloss.
9. The program product according to claim 7, wherein with respect to the evaluation, when an average of luminance of a peripheral region including the determined positions is high and uniformity is low, the evaluation is reflection.
10. The program product according to claim 7, wherein with respect to the evaluation, when an average of luminance of a peripheral region including the determined positions is high and uniformity is high, the evaluation is gloss.
11. The program product according to claim 7, wherein with respect to the evaluation, when luminance of an upper semicircular region of a circle centered on the determined positions is the same as or higher than luminance of a lower semicircular region of the circle, the evaluation is beautiful gloss.
12. The program product according to claim 7, wherein with respect to the evaluation, when luminance of a lower semicircular region of a circle centered on the determined positions is higher than luminance of an upper semicircular region of the circle, the evaluation is distorted gloss.
13. The program product according to claim 3, wherein the program causes the computer to further execute the following processing: based on the determined position and the outer corner of the subject, to evaluate a change in the position caused by the relaxation.
14. The program product according to claim 1, wherein, The program causes the computer to further execute the process of: displaying information related to beauty corresponding to the estimated region.
15. An evaluation device comprising: a cheek data acquisition unit that acquires data representing at least a cheek of a subject, an estimation unit that estimates, when viewed from any position from a front of the subject to 90 degrees right and to 90 degrees left, all regions of a cheek portion of the subject in which a direction vector from a center point of the head of the subject through a cheek surface toward an observer coincides with a normal vector of the cheek surface in a cheek portion seen in the near distance.
16. A method executed by an evaluation device, wherein, acquiring data representing at least a cheek of a subject, estimating, when viewed from any position from a front of the subject to 90 degrees right and to 90 degrees left, all regions of a cheek portion of the subject in which a direction vector from a center point of the head of the subject through a cheek surface toward an observer coincides with a normal vector of the cheek surface in a cheek portion seen in the near distance.