Method for operating information processing device, information processing device, and program

Abstract

To improve accuracy of an analysis of secular changes in features in face portions.SOLUTION: A method for operating an information processing device includes: a first step of generating a feature matrix which is a matrix including a vector of each of a plurality of portions having as components a plurality of feature quantities of each of the portions of a face extracted from an image of the face of a person; a second step of deriving a transformation matrix to be multiplied by a first feature matrix based on the image of the face of the person in a first period to derive a second feature matrix based on the image of the face of the person in a second period after the first period, on the basis of the first and second feature matrices; a third step of deriving secular vectors which are predetermined eigenvectors of the transformation matrix; and a fourth step of generating information in which the secular vectors corresponding to respective images of the faces of the persons are classified into groups on a circular coordinate system.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an operation method of an information processing device, an information processing device, and a program. [Background technology]

[0002] Changes over time, such as wrinkles and pigmentation, occur in areas of a person's face, such as the corners of the eyes, cheeks, and mouth. These changes affect a person's appearance and are therefore a matter of cosmetic concern. Various techniques have been proposed for analyzing and predicting such changes in facial areas over time (e.g., Patent Documents 1 to 3). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2019-114253 [Patent Document 2] Special table number 2020-515952 [Patent Document 3] Patent Publication No. 2015-062569 Summary of the Invention [Problem to be solved by the invention]

[0004] There is room for improvement in the accuracy of analyzing changes in facial features over time.

[0005] In view of the above, the following discloses an operation method of an information processing device that can improve the accuracy of analyzing changes over time in features of facial parts. [Means for solving the problem]

[0006] In order to solve the above problem, the method of operating an information processing device disclosed herein includes a first step of generating a feature matrix, which is a matrix including vectors for multiple parts of a face, the components of which are multiple feature amounts for each part of the face extracted from an image of the person's face; a second step of deriving a transformation matrix, based on the first and second feature matrices, to multiply the first feature matrix based on the image of the person's face at a first time period by the transformation matrix to derive a second feature matrix based on an image of the person's face at a second time period after the first time period; a third step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix; and a fourth step of generating information in which the multiple aging vectors, each corresponding to a multiple image of the person's face, are divided into groups in a circular coordinate system.

[0007] The information processing device of the present disclosure also has a control unit that executes the following steps: a first step of generating a feature matrix, which is a matrix including vectors for each part of a face, the components of which are multiple feature amounts for each part of the face extracted from an image of a person's face; a second step of deriving a transformation matrix, based on the first and second feature matrices, to multiply the first feature matrix based on the image of the person's face at a first time period by the transformation matrix to derive a second feature matrix based on an image of the person's face at a second time period after the first time period; a third step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix; and a fourth step of generating information in which the multiple aging vectors, each corresponding to a multiple image of the person's face, are divided into groups in a circular coordinate system.

[0008] Furthermore, the program of the present disclosure is a program that, when executed by an information processing device, causes the information processing device to execute the following steps: a first step of generating a feature matrix, which is a matrix including vectors for multiple parts of a face, the components of which are multiple feature amounts for each part of the face extracted from an image of a person's face; a second step of deriving a transformation matrix, based on the first and second feature matrices, to multiply the first feature matrix based on the image of the person's face at a first time period by the transformation matrix to derive a second feature matrix based on an image of the person's face at a second time period after the first time period; a third step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix; and a fourth step of generating classification information in which the multiple aging vectors, each corresponding to a multiple image of the person's face, are classified into groups in a circular coordinate system. [Effects of the Invention]

[0009] According to the operation method of the information processing device and the like in the present disclosure, it is possible to improve the accuracy of analyzing changes over time in features of facial parts. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 illustrates an example of the configuration of an information processing system. [Figure 2] FIG. 10 is a flowchart illustrating an example of an operation procedure of the server device. [Figure 3] FIG. 1 is a diagram illustrating examples of facial parts. [Figure 4] FIG. 10 is a diagram illustrating an example of display of information output by the server device. [Figure 5] 10A and 10B are diagrams illustrating an example of display of information output by a server device in a modified example. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of the present invention will be described.

[0012] [System Configuration] FIG. 1 is a diagram illustrating an example configuration of an embodiment of the present invention. The information processing system 1 includes a server device 10 and a terminal device 12 connected to each other via a network 11 so as to be able to communicate with each other. In the information processing system 1, the server device 10 performs information processing, including machine learning, using various information sent from the terminal device 12. The terminal device 12 is, for example, one or more personal computers. The personal computer may include a tablet terminal device, a smartphone, etc. The server device 10 corresponds to the "information processing device" in this embodiment. The server device 10 is, for example, one or more server computers. When the server device 10 is a single server computer, the server device 10 may be multiple server computers that cooperate to execute the operations of this embodiment and provide a cloud service. The network 11 is, for example, a local area network (LAN), the Internet, an ad hoc network, a metropolitan area network (MAN), a mobile communication network, or other networks, or any combination thereof.

[0013] In this embodiment, the server device 10 performs information processing to analyze changes over time in feature amounts for each facial part extracted from a person's face image (hereinafter referred to as a face image). The face image is a captured image obtained by capturing an image of the person's face. The server device 10 executes a step of generating a feature matrix (hereinafter referred to as a feature matrix generation step), which is a matrix including vectors for each of a plurality of parts, the components of which are the feature amounts for each facial part extracted from the face image. The server device 10 also executes a step of deriving a transformation matrix based on the first and second feature matrices (hereinafter referred to as a transformation matrix derivation step), which is multiplied by a first feature matrix based on an image of the person's face at a first time point to derive a second feature matrix based on an image of the person's face at a second time point after the first time point. The server device 10 also executes a step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix (hereinafter referred to as an aging vector derivation step). The server device 10 then executes a step (hereinafter referred to as a segmentation information generation step) of generating information (hereinafter referred to as segmentation information) in which a plurality of aging vectors corresponding to the facial images of a plurality of people are segmented into groups in a circular coordinate system. According to this embodiment, the server device 10 outputs information for analyzing the correlation between changes over time in each facial part in facial images of a person taken at different times. This makes it possible to improve the accuracy of analyzing changes over time in features of facial parts.

[0014] [Configuration example of server device 10] The server device 10 includes a communication unit 101, a storage unit 102, a control unit 103, an input unit 105, and an output unit 106. When the server device 10 is configured with two or more server computers, these components are appropriately arranged in the two or more server computers.

[0015] The communication unit 101 includes one or more communication interfaces. The communication interface is, for example, a LAN interface. The communication unit 101 receives information used in the operation of the server device 10 and transmits information obtained by the operation of the server device 10. The server device 10 is connected to a network 11 by the communication unit 101 and communicates information with a terminal device 12 via the network 11.

[0016] The storage unit 102 includes, for example, one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these, that function as a main storage device, an auxiliary storage device, or a cache memory. The semiconductor memories are, for example, RAM (Random Access Memory) or ROM (Read Only Memory). The RAM is, for example, SRAM (Static RAM) or DRAM (Dynamic RAM). The ROM is, for example, EEPROM (Electrically Erasable Programmable ROM). The storage unit 102 stores information used in the operation of the control unit 103 and information obtained by the operation of the control unit 103.

[0017] The control unit 103 includes one or more processors, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit), or a dedicated processor such as a GPU (Graphics Processing Unit) specialized for a specific process. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), etc. The control unit 103 executes information processing related to the operation of the server device 10 while controlling each unit of the server device 10.

[0018] The functions of the server device 10 are realized by a processor included in the control unit 103 executing a control program. The control program is a program for causing the processor to function as the control unit 103. Alternatively, some or all of the functions of the server device 10 may be realized by a dedicated circuit included in the control unit 103. Alternatively, the control program may be stored in a non-transitory recording / storage medium readable by the control unit 103, and read by the control unit 103 from the medium.

[0019] The input unit 105 includes one or more input interfaces. The input interfaces are, for example, physical keys, capacitance keys, a pointing device, a touch screen integrated with a display, or a microphone that accepts voice input. The input unit 105 accepts an operation to input information used in the operation of the server device 10 and sends the input information to the control unit 103.

[0020] The output unit 106 includes one or more output interfaces. The output interface is, for example, a display or a speaker. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display. The output unit 106 outputs information obtained by the operation of the server device 10.

[0021] [Configuration example of terminal device 12] The terminal device 12 includes a communication unit 121 , a storage unit 122 , a control unit 123 , an input unit 125 , and an output unit 126 .

[0022] The communication unit 121 includes a communication module compatible with wired or wireless LAN standards, a module compatible with mobile communication standards such as LTE, 4G, 5G, etc. The terminal device 12 is connected to the network 11 by the communication unit 121 via a nearby router device or a mobile communication base station, and performs information communication with the server device 10, etc. via the network 11.

[0023] The storage unit 122 includes one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these. The semiconductor memories are, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The storage unit 122 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 122 stores information used in the operation of the control unit 123 and information obtained by the operation of the control unit 123.

[0024] The control unit 123 has, for example, one or more general-purpose processors such as a CPU, an MPU (Micro Processing Unit), etc., or one or more dedicated processors such as a GPU specialized for a specific process. Alternatively, the control unit 123 may have one or more dedicated circuits such as an FPGA, an ASIC, etc. The control unit 123 performs overall control of the operation of the terminal device 12 by operating according to a control / processing program or operating according to an operating procedure implemented as a circuit. The control unit 123 then transmits and receives various information to and from the server device 10, etc. via the communication unit 121, and performs the operation according to this embodiment.

[0025] The functions of the terminal device 12 are realized by a processor included in the control unit 123 executing a control program. The control program is a program for causing the processor to function as the control unit 123. Alternatively, some or all of the functions of the terminal device 12 may be realized by a dedicated circuit included in the control unit 123. Alternatively, the control program may be stored in a non-transitory recording / storage medium readable by the control unit 123, and read by the control unit 123 from the medium.

[0026] The input unit 125 includes one or more input interfaces. The input interfaces include, for example, physical keys, capacitive keys, a pointing device, and a touch screen integrated with a display. The input interfaces also include a microphone for receiving voice input and a camera for capturing captured images. The input interfaces may also include a scanner or camera for scanning image codes, and an IC card reader. The input unit 125 receives an operation for inputting information used in the operation of the control unit 123 and sends the input information to the control unit 123. The input unit 125 also sends images captured by the camera to the control unit 123.

[0027] The output unit 126 includes one or more output interfaces. The output interfaces include, for example, a display and a speaker. The display is, for example, an LCD or an organic EL display. The output unit 126 outputs information obtained by the operation of the control unit 123.

[0028] [Operation procedure of server device 10] 2 is a flowchart illustrating an example of the operation of the server device 10. Each step is executed by the control unit 103.

[0029] In step S20, the control unit 103 acquires a plurality of pairs of facial images over time. The facial images are generated by capturing an image of a person's face. The pair of facial images over time is a pair of facial images of the same person captured at two different times. The image of the person's face is captured by, for example, the terminal device 12. For example, the control unit 103 receives pairs of facial images over time of each of a plurality of people sent from the terminal device 12 via the communication unit 101 and stores them in the storage unit 102. The control unit 103 may acquire a plurality of pairs of facial images over time from open data. The control unit 103 stores the acquired facial images in the storage unit 102 together with identification information that uniquely identifies each facial image. At this time, the control unit 103 associates pairs of facial images over time of the same person and stores them in the storage unit 102.

[0030] In step S21, the control unit 103 extracts feature amounts for each part of the facial image. The control unit 103 extracts a facial region of the facial image using an arbitrary algorithm, detects parts of the face such as the eyes, nose, and mouth, and identifies the parts from which feature amounts are extracted. For example, as shown in the example of FIG. 3, parts 31 to 36 are identified in the facial image 3. Each part is an area of ​​arbitrary size, for example, part 31 is the forehead, part 32 is the space between the eyebrows, part 33 is the corner of the eye, part 34 is the area under the eye, part 35 is the area around the mouth where so-called marionette lines occur, and part 36 is the area of ​​the cheek where nasolabial folds occur. Parts 33, 34, 35, and 36 may be on either the left or right side, or both. The feature amount is a score indicating the degree of a feature that develops over time in each part, and includes multiple values ​​obtained by image processing. The feature amount is, for example, the degree of wrinkles. The control unit 103 performs any image processing on the regions 31 to 36 to derive the degree of wrinkles, i.e., feature amounts, based on, for example, the proportion of areas of colors that can be recognized as wrinkles in each region. Alternatively, the feature amount may be, for example, the degree of age spots. In this case, the degree of age spots is determined based on the proportion of areas of colors that can be recognized as age spots in each region. The control unit 103 performs processing to extract feature amounts for each pair of facial images of multiple people. Note that the feature amount may include a visual evaluation score. Such evaluation score is, for example, input to the terminal device 12 by the inspector, sent to the server device 10, and stored in association with the facial image of the person.

[0031] In step S22, the control unit 103 executes a feature matrix generation step of generating a feature matrix. The control unit 103 generates a feature matrix for each face image, which is a matrix including vectors for multiple body parts, each of which has multiple feature amounts for each body part as components. For example, the control unit 103 generates l vectors (l is a natural number) for l body parts, each of which has i values ​​(i is a natural number) corresponding to the feature amounts of each body part. TIFF2025131425000002.tif9120 (t represents the time of capture) is generated using an arbitrary algorithm, and a feature matrix of 1 × l is generated if the dimension of the feature including these is 1, and an l × l feature matrix is ​​generated if the dimension of the feature has two or more dimensions using a Gram matrix. TIFF2025131425000003.tif10166 is generated. The control unit 103 also generates a feature matrix for each pair of face images over time. That is, the control unit 103 generates a feature matrix Feature matrix after time T has elapsed since image capture time t, paired with TIFF2025131425000004.tif946 TIFF2025131425000005.tif946 is generated. The control unit 103 stores the generated feature matrix in the storage unit 102. At this time, the control unit 103 stores the feature matrix corresponding to a pair of facial images of the same person over time. TIFF2025131425000006.tif945 and feature matrix Store it in association with TIFF2025131425000007.tif968.

[0032] In step S23, the server device 10 executes a transformation matrix derivation step of deriving a transformation matrix for each pair of feature matrices corresponding to a pair of face images of the same person over time. Multiply by TIFF2025131425000008.tif950 to get the feature matrix at time (t+T) The transformation matrix to derive TIFF2025131425000009.tif1040 is the feature matrix The control unit 103 derives the transformation matrix F by using an arbitrary algorithm so that the following (Equation 1) holds: is derived by calculating (Equation 2) or (Equation 3) according to the dimension of i. TIFF2025131425000011.tif7147

[0033] If the dimension of i is 1, that is, When TIFF2025131425000012.tif8164 is one-dimensional information such as a visual evaluation score of a part, the control unit 103 obtains F by (Equation 2). TIFF2025131425000013.tif26159

[0034] If the dimension of i is 2 or more, that is, When TIFF2025131425000014.tif6123 is information having two or more dimensions such as a visual evaluation score of a part, the control unit 103 TIFF2025131425000015.tif9165 is converted to an l×l matrix by a Gram matrix Create TIFF2025131425000016.tif9158 and calculate F by (Equation 3). Ask for. TIFF2025131425000017.tif14142

[0035] The control unit 103 stores the derived transformation matrix in the storage unit 102 in association with the face image pair corresponding to the pair of feature matrices.

[0036] In step S24, the control unit 103 executes an aging vector derivation step of deriving an aging vector, which is a predetermined eigenvector for each transformation matrix. The control unit 103 derives, for each face image pair, the eigenvector having the largest eigenvalue among the eigenvectors of the transformation vectors, using an arbitrary algorithm.

[0037] In step S25, the control unit 103 executes a classification information output step of outputting classification information in which a plurality of aging vectors corresponding to a plurality of facial image pairs are classified into groups in a circular coordinate system. The control unit 103 performs a process of clustering the plurality of aging vectors into groups of similar angles as angle data exhibiting a von Mises-Fisher distribution in the circular coordinate system. The control unit 103 associates identification information of the clustered groups with the aging vectors classified into the groups and stores the identification information in the storage unit 102 as classification information.

[0038] In step S26, the control unit 103 outputs the sorting information. The control unit 103 sends the sorting information to the terminal device 12 used by the analyst (hereinafter simply referred to as the user). The terminal device 12 displays the sorting information, allowing the user to confirm the sorting information.

[0039] FIG. 4 is an example of displayed classification information. In the example of FIG. 4, when the aging vectors are classified into three groups, "Group 1," "Group 2," and "Group 3," representative values ​​of wrinkle scores for each part of the face image belonging to each group are displayed. For each group, control unit 103 reads out from storage unit 102 a pair of feature matrices corresponding to the aging vectors classified into that group, that is, information on the feature matrix of the face image at time t and the feature matrix of the face image at time (t+T). Each feature matrix contains a vector whose components are feature quantities that represent the degree of wrinkles for each part of the face. TIFF2025131425000018.tif6132 is included. The control unit 103 derives a representative value of vector components for each body part using an arbitrary algorithm. Furthermore, the control unit 103 derives a further representative value (e.g., average value; hereinafter referred to as group representative value) of the representative values ​​for each body part in a feature matrix corresponding to face images of multiple people in the group at time t. The control unit 103 also derives a group representative value of the representative values ​​for each body part in a feature matrix corresponding to face images of multiple people in the group at time (t+T). Furthermore, the control unit 103 derives a representative value of the difference for each pair of time-lapse data between the representative value at time t and the representative value at time (t+T) for each body part in the group (e.g., average of the differences for multiple pairs of representative values). Figure 4 shows the group representative values ​​and differences at time points t and (t+T) for each of the areas "laugh lines," "forehead," "between the eyebrows," "under the eyes," "marionette lines," and "right corner of the eye" for each of the groups "Group 1," "Group 2," and "Group 3."

[0040] By checking the classification information as shown in FIG. 4, the user can identify, for example, areas where significant changes over time have occurred for each group. For example, for a person belonging to "Group 1," as shown by the underlined representative values ​​in "Difference," it is confirmed that changes over time are relatively large in the areas "under the eyes" and "right outer corner of the eye," and that wrinkles have increased in these areas. Also, for a person belonging to "Group 2," as shown by the underlined representative values ​​in "Difference," it is confirmed that changes over time are relatively large in the areas "laugh lines," "under the eyes," and "right outer corner of the eye," and that wrinkles have increased in these areas. Furthermore, for a person belonging to "Group 3," as shown by the underlined representative values ​​in "Difference," it is confirmed that changes over time are relatively large in the area "laugh lines," and that wrinkles have increased in these areas.

[0041] According to this embodiment, by using a feature matrix and a transformation matrix, it is possible to model how the aging of a certain part is affected by the feature quantities of other parts, and to verify the state of aging of each part.

[0042] [Example 1] In one embodiment, the server device 10 acquires facial condition measurements of a person whose facial image is captured. The facial condition measurements include, for example, moisture content, sebum content, transepidermal water loss, spectral reflectance, and the like, which reflect the internal condition of parts such as the forehead and cheeks. For example, when capturing facial images of a person at different times t and t+T, an examiner measures the moisture content of each part using a suitable measuring device and inputs the results into the terminal device 12. When these measurements are sent to the server device 10, they are stored in the storage unit 102 in association with the identification information of the corresponding facial image. The control unit 103 of the server device 10 aggregates and processes the facial condition measurements into groups based on the classification information, and sends the measurement information to the terminal device 12 to present to the user together with the classification information. The terminal device 12 then displays the measurement information to the user.

[0043] FIG. 5 shows an example of displayed measurement value information. The example in FIG. 5 shows part of the classification information shown in FIG. 4, namely, classification information extracted from the representative values ​​of each body part in the three groups "Group 1," "Group 2," and "Group 3" in descending order of difference for two or more groups, and a representative value of the measurement value corresponding to each group (for example, the average value of the measurement values ​​of the person classified into the group). The representative values ​​of the measurement values ​​are the representative value of the forehead moisture content, cheek moisture content, and forehead sebum content at time t and (t+T) respectively, and the representative value of the difference (average value of the group). The number and type of body parts for which scores are displayed can be set by the user from terminal device 12, and information according to the setting can be output by server device 10.

[0044] By checking the classification information and measurement value information as shown in Figure 5, the user can, for example, confirm the correlation between the areas with significant changes over time for each group and the measurement values. For example, for a person belonging to "Group 1," it is confirmed that the areas "under the eyes," "right outer corner of the eye," and "nasolabial folds" show relatively large changes over time, and that the moisture content of the forehead has decreased over time. This suggests that, for example, a decrease in moisture content of the forehead may affect the increase in wrinkles under the eyes, right outer corner of the eye, and nasolabial folds. Furthermore, for a person belonging to "Group 2," it is confirmed that the areas "nasolabial folds," "under the eyes," and "right outer corner of the eye" show relatively large changes over time, and that the moisture content of the cheeks has decreased over time. This suggests that, for example, a decrease in moisture content of the cheeks may affect the increase in wrinkles under the eyes, right outer corner of the eye, and nasolabial folds. Furthermore, for a person belonging to "Group 3," it is confirmed that the areas "nasolabial folds" and "under the eyes" show relatively large changes over time, and that the amount of sebum on the cheeks has decreased over time. Therefore, for example, it is suggested that a decrease in the amount of sebum on the forehead may contribute to an increase in nasolabial folds and wrinkles under the eyes.

[0045] [Example 2] In another embodiment, the server device 10 can classify the trends of aging in facial features of a new person, such as a subject, using a pair of facial images over time of the person. When the terminal device 12 generates a pair of facial images by capturing images of the subject's face over time, the server device 10 acquires the pair of facial images of the subject over time from the terminal device 12. The control unit 103 of the server device 10 then executes a feature matrix generation process, a transformation matrix derivation process, and an aging vector derivation process for the pair of facial images of the subject, and determines to which of the previously classified groups the obtained aging vector belongs in a circular coordinate system. The server device 10 then sends classification information corresponding to the determined group to the terminal device 12 for presentation to the subject. By checking the information displayed on the terminal device 12, the subject can obtain information regarding the trends in their facial features.

[0046] According to the above-described embodiment, by modeling the influence of aging changes in a certain facial region on the features of other regions and examining the aging changes in each region, a user can examine in detail the trends in changes in each facial region over time. Furthermore, it is possible for a subject to grasp the trends in their own facial regions. This makes it possible to improve the accuracy of analyzing changes in facial features over time. Furthermore, the results derived from this can be used as evaluation criteria for visually checking daily changes in skin condition. Therefore, in analyzing changes in facial features over time, not only can the accuracy be improved but also new insights and analytical expression methods can be obtained from measurement data.

[0047] In the above description, the server device 10 corresponds to the "information processing device." However, the server device 10 and the terminal device 12 may cooperate to configure the "information processing device," or the terminal device 12 may correspond to the "information processing device."

[0048] In the above-described embodiment, the processing / control program that defines the operation of the terminal device 12 may be stored in the memory unit 102 of the server device 10 or in the memory unit of another server device, and may be downloaded to the terminal device 12 via the network 11, or may be stored in a computer-readable non-transitory recording / storage medium and read by the terminal device 12 from the medium.

[0049] Although the embodiments have been described above based on the drawings and examples, it should be noted that those skilled in the art can easily make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each means, step, etc. can be rearranged so as not to be logically inconsistent, and multiple means, steps, etc. can be combined or divided into one. [Explanation of symbols]

[0050] 10: Server device 11: Network 12: Terminal device 101, 121: Communications Department 102, 122: Storage section 103, 123: control unit 105, 125: Input section 106, 126: Output section

Claims

1. A method for operating an information processing device, comprising: a first step of generating a feature matrix, which is a matrix including a plurality of vectors for each part of a face, the components of which are a plurality of feature amounts for each part of the face extracted from an image of the face of a person; a second step of deriving a transformation matrix based on the first and second feature matrices, the transformation matrix being used to multiply a first feature matrix based on an image of the person's face at a first time point by the transformation matrix to derive a second feature matrix based on an image of the person's face at a second time point after the first time point; a third step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix; a fourth step of generating information in which the plurality of aging vectors corresponding to the plurality of face images of the person are divided into groups in a circular coordinate system; A method of operation having the following steps:

2. In claim 1, the fourth step includes generating information in which information on measurement values ​​of the person's face is associated with the group to which the aging vector corresponding to the image of the face belongs; How it works.

3. In claim 1 or claim 2, a fifth step of performing the first to third steps using images of the face of the first person generated at different times to derive a first aging vector corresponding to the image of the face of the first person; a sixth step of outputting information about a first group to which the first aging vector belongs in the circular coordinate system; The method of operation further comprises:

4. An information processing device having a control unit, The control unit a first step of generating a feature matrix, which is a matrix including a plurality of vectors for each part of a face, the components of which are a plurality of feature amounts for each part of the face extracted from an image of the face of a person; a second step of deriving a transformation matrix based on the first and second feature matrices, the transformation matrix being used to multiply a first feature matrix based on an image of the person's face at a first time point by the transformation matrix to derive a second feature matrix based on an image of the person's face at a second time point after the first time point; a third step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix; a fourth step of generating information in which the plurality of aging vectors corresponding to the plurality of face images of the person are divided into groups in a circular coordinate system; To execute Information processing device.

5. In claim 4, In the fourth step, the control unit generates information in which information on the measurement values ​​of the person's face is associated with the group to which the aging vector corresponding to the image of the face belongs. Information processing device.

6. In claim 4 or claim 5, The control unit a fifth step of performing the first to third steps using images of the face of the first person generated at different times to derive a first aging vector corresponding to the image of the face of the first person; a sixth step of outputting information about a first group to which the first aging vector belongs in the circular coordinate system; Further execute Information processing device.

7. A program for an information processing device, When executed by an information processing device, the information processing device a first step of generating a feature matrix, which is a matrix including a plurality of vectors for each part of a face, the components of which are a plurality of feature amounts for each part of the face extracted from an image of the face of a person; a second step of deriving a transformation matrix based on the first and second feature matrices, the transformation matrix being used to multiply a first feature matrix based on an image of the person's face at a first time point by the transformation matrix to derive a second feature matrix based on an image of the person's face at a second time point after the first time point; a third step of deriving an aging vector, which is a predetermined eigenvector of the transformation matrix; a fourth step of generating classification information by classifying the aging vectors corresponding to the face images of the plurality of people into groups in a circular coordinate system; To execute Program.

8. In claim 7, the fourth step includes generating information in which information on measurement values ​​of the person's face is associated with the group to which the aging vector corresponding to the image of the face belongs; program.

9. In claim 7 or claim 8, a fifth step of performing the first to third steps using images of the face of the first person generated at different times to derive a first aging vector corresponding to the image of the face of the first person; a sixth step of outputting information about a first group to which the first aging vector belongs in the circular coordinate system; and causing the information processing to further execute the above. Program.

Images