Facial expression support device, facial expression support method, and program

Abstract

By selecting appropriate target images, it supports facial expression training. [Solution] The facial expression support device extracts feature quantities from the user's facial image to identify the user's face. Based on these feature quantities, the facial expression support device extracts facial images with the desired expression from the user's terminal device and the social networking service (SNS) the user uses as target images. Based on a third-party evaluation of the target images, the facial expression support device selects and outputs a target image from among the target images.

Description

Technical Field

[0001] The present disclosure relates to a support technology for creating expressions.

Background Art

[0002] In situations where there are many people met for the first time, such as when entering school or starting a new job, many people try to improve their impression by showing more smiles. Also, in business-related face-to-face situations such as job interview activities and online meetings, expressions and ways of speaking also affect the results. Therefore, there are people who are troubled because they cannot create appropriate expressions suitable for the situation. Patent Document 1 describes a system that searches for an image including a face with a desired expression from a large number of images.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, there is a known service for expression training by using an expression recognition technology to take a picture of oneself with a camera while looking at a target expression image. However, in this service, since a general target expression image that is statistically considered good is used, it may not be helpful for the person undergoing training.

[0005] One of the objectives of the present disclosure is to support expression training by selecting an appropriate target image.

Means for Solving the Problems

[0006] To solve the above problems, from one aspect of the present disclosure, an expression support device A feature extraction means for extracting features from a user's facial image to identify the user's face, Based on the aforementioned features, a target image extraction means extracts a facial image with the desired expression from the terminal device used by the user and the social networking service used by the user as the target image. A target image selection means selects and outputs a target image from among the target images based on a third-party evaluation of the target image, It is equipped with.

[0007] In other aspects of this disclosure, the facial expression support method performed by the facial expression support device is: From the user's facial image, feature quantities are extracted to identify the user's face. Based on the aforementioned features, facial images with the desired expression are extracted as target images from the terminal device used by the user and the social networking service used by the user. Based on a third-party evaluation of the aforementioned target images, a target image is selected from the aforementioned target images and output.

[0008] In yet another aspect of this disclosure, a program executed by a facial expression support device equipped with a computer is: From the user's facial image, feature quantities are extracted to identify the user's face. Based on the aforementioned features, facial images with the desired expression are extracted as target images from the terminal device used by the user and the social networking service used by the user. Based on a third-party evaluation of the aforementioned target images, the computer is instructed to perform a process of selecting and outputting a target image from among the aforementioned target images. [Effects of the Invention]

[0009] According to this disclosure, facial expression training can be supported by selecting an appropriate target image. [Brief explanation of the drawing]

[0010] [Figure 1] This document shows an example of the general configuration of the facial expression support system described herein. [Figure 2] A block diagram showing an example of the hardware configuration of a server and user terminal. [Figure 3] This is an example of a server's functional configuration. [Figure 4] This diagram schematically illustrates the information sent from the user terminal to the server. [Figure 5] This is an example of a display screen. [Figure 6] This flowchart shows an example of image selection processing. [Figure 7] This is a block diagram showing an example of another functional configuration for a facial expression support device. [Figure 8] Here is a flowchart showing another example of image selection processing. [Modes for carrying out the invention]

[0011] Embodiments of this disclosure will be described below with reference to the drawings. [First Embodiment] (Overall structure) Figure 1 shows an example of the schematic configuration of the facial expression support system 100 to which the facial expression support device of this disclosure is applied. The facial expression support system 100 is a system that supports facial expression training by the user by selecting and displaying a target image of the ideal facial expression that the user desires, based on evaluations by a third party. Specifically, the facial expression support system 100 extracts a face image of the desired expression as a target image, for example, from images including the user's own face posted on SNS (social networking service) (hereinafter also referred to as "face image") or from face images of people similar to the user that exist on the internet. Next, the facial expression support system 100 selects a target image from the target images, taking into consideration evaluations by a third party such as the number of views, and displays it on the user's terminal device.

[0012] In the facial expression support system 100 shown in Figure 1, the server 1 and the user terminal 2 are connected via a network 5 such as the Internet. The user is a person who undergoes training to create appropriate facial expressions in various situations.

[0013] The user terminal 2 is a smartphone, tablet, PC, etc. used by the user, and transmits input information such as the user's face image and desired expression to the server 1, or receives a target image from the server 1. The user terminal 2 is an example of the terminal device used by the user of the present disclosure.

[0014] The server 1 is an information processing device that performs processing, storage, and transmission / reception of various data. It receives the user's face image and input information from the user terminal 2, or selects a target image suitable for the user's expression training and transmits it to the user terminal 2. Note that the server 1 may be a virtual server existing in a cloud environment. The server 1 is an example of the expression support device of the present disclosure.

[0015] (Hardware Configuration) FIG. 2(a) is a block diagram showing an example of the hardware configuration of the server 1. As shown in the figure, the server 1 includes an interface 11, a processor 12, a memory 13, a recording medium 14, a display unit 15, and an input unit 16.

[0016] The interface 11 exchanges data with the user terminal 2. The interface 11 is used when receiving the user's face image and input information from the user terminal 2, or transmitting a target image suitable for the user's expression training to the user terminal 2.

[0017] Processor 12 is a computer such as a CPU (Central Processing Unit) that controls the entire server 1 by executing pre-prepared programs. Processor 12 can be a CPU, GPU (Graphics Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Point Number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination of these.

[0018] Memory 13 consists of ROM (Read Only Memory), RAM (Random Access Memory), and other components. Memory 13 stores programs executed by the processor 12. Memory 13 is also used as working memory while the processor 12 is executing various processes.

[0019] The recording medium 14 is a non-volatile, non-temporary recording medium such as a disk-shaped recording medium or semiconductor memory, and is configured to be detachable from the server 1. The recording medium 14 stores various programs that the processor 12 executes. When the server 1 performs image selection processing, the programs stored on the recording medium 14 are loaded into memory 13 and executed by the processor 12.

[0020] The display unit 15 displays a predetermined image, for example, using an LCD (Liquid Crystal Display). The input unit 16 is used by the operator managing server 1, and can be a keyboard, mouse, touch panel, etc.

[0021] Figure 2(b) is a block diagram showing an example of the hardware configuration of user terminal 2. As shown in the figure, user terminal 2 includes an interface 21, a processor 22, a memory 23, a recording medium 24, a display unit 25, an input unit 26, and an imaging unit 27.

[0022] Interface 21 exchanges data with Server 1 via Network 5. Interface 21 is used to send input information such as the user's face image and desired facial expression to Server 1, and to receive target images from Server 1.

[0023] The processor 22 is a computer such as a CPU, and controls the entire user terminal by executing pre-prepared programs. The processor 22 can be a CPU, GPU, DSP, MPU, FPU, PPU, TPU, quantum processor, microcontroller, or a combination of these.

[0024] Memory 23 is composed of ROM, RAM, etc. Memory 23 stores programs executed by the processor 22. Memory 23 is also used as working memory while the processor 22 is executing various processes.

[0025] The recording medium 24 is a non-volatile, non-temporary recording medium such as a disk-shaped recording medium or semiconductor memory, and is configured to be detachable from the user terminal 2. The recording medium 24 stores various programs executed by the processor 22. The display unit 25 is, for example, an LCD, which displays a predetermined image. The input unit 26 is a touch panel or the like, which is used when the user performs a predetermined operation. The imaging unit 27 is equipped with a camera and acquires captured still image data and video data as images.

[0026] (Functional Configuration) Figure 3 is a block diagram showing an example of the functional configuration of Server 1. Functionally, Server 1 comprises a face image acquisition unit 41, an input information acquisition unit 42, a feature extraction unit 43, a target image extraction unit 44, and a target image selection unit 45.

[0027] The face image acquisition unit 41, input information acquisition unit 42, feature extraction unit 43, target image extraction unit 44, and target image selection unit 45 are realized by the processor 12 executing a program.

[0028] The face image acquisition unit 41 acquires a face image of the user performing facial expression training. The face image may be either still image data or video data. The user sends their own face image, which they have already acquired, or a face image of the user taken by the user terminal 2, to the server 1 by performing a predetermined operation using the user terminal 2.

[0029] The input information acquisition unit 42 acquires input information that indicates the facial expression desired by the user. The input information is text or an image that indicates the facial expression the user wants to make. If it is difficult for the user to verbalize the facial expression they want to make, they may input an image of another person's face making the desired expression, and the input information will include one or more of either text or an image. For example, if the desired facial expression is "smiling," the user will use the user terminal 2 to perform a predetermined operation and send the text "smiling" or an image of a smiling face as input information to the server 1. The text can be freely written to describe the scene or situation the user envisions, such as "a smile that makes a good impression on someone you meet for the first time" or "a facial expression when moderating a meeting." Furthermore, the facial expression desired by the user is not limited to positive expressions such as smiling, but can be arbitrarily set to negative expressions such as an angry face.

[0030] Figure 4 is a schematic diagram illustrating the information transmitted from the user terminal 2 to the server 1. As shown in Figure 4, the user uses the user terminal 2 to perform a predetermined operation and transmits to the server 1 an image of their face, along with one or more text and / or images indicating a desired facial expression.

[0031] The feature extraction unit 43 extracts features from the user's face image to identify the user's face. Various known features can be used as features, such as those used in facial recognition technology. In this disclosure, the feature extraction unit 43 causes the server 1 to extract features from the user's face image, but this disclosure is not limited to this, and the user terminal 2 may extract features from the user's face image and send them to the server 1. Thus, the method by which the server 1 acquires features can be arbitrarily set.

[0032] The target image extraction unit 44 extracts a target image based on the feature quantities used to identify the user's face and the input information. Specifically, the target image extraction unit 44 determines the feature quantities corresponding to the facial expression desired by the user based on the feature quantities used to identify the user's face and the input information. For example, if the user enters the text "smile" as input information, the target image extraction unit 44 modifies the feature quantities extracted from the user's face image to the feature quantities corresponding to a smile, and generates feature quantities corresponding to the facial expression (smile) desired by the user.

[0033] Furthermore, if the user inputs a facial image of another person with the desired expression as input information, the target image extraction unit 44 modifies the feature quantities extracted from the user's facial image with the feature quantities extracted from the facial image of another person with the desired expression, thereby generating feature quantities corresponding to the expression desired by the user.

[0034] Furthermore, if the facial expression desired by the user is, for example, "the facial expression when chairing a meeting," the target image extraction unit 44 extracts a model facial image of the desired scene or situation from the internet or other sources, and extracts feature quantities from that facial image. Next, the target image extraction unit 44 modifies the feature quantities extracted from the model facial image with respect to the feature quantities extracted from the user's facial image, and generates feature quantities corresponding to the facial expression desired by the user (when chairing a meeting).

[0035] The target image extraction unit 44 then uses feature quantities corresponding to the facial expression desired by the user to extract face images with the desired facial expression as target images from images on the internet, including social networking services used by the user, or from images stored on the user's terminal device. Specifically, the target image extraction unit 44 extracts images that have feature quantities similar to the feature quantities corresponding to the facial expression desired by the user as target images. The target image extraction unit 44 may download and obtain the target face images, or it may create a list of links to those images.

[0036] Here, the SNS used by the user is a service that allows users to post images and comments on the internet and connect with friends and other individuals. The terminal device used by the user is a smartphone or tablet, including user terminal 2. As a result, the target image extraction unit 44 can extract a facial image with the desired expression from the facial images of the user posted on the SNS as the target image. The target image is not limited to still image data, but may also be an image that captures a momentary facial expression from video data.

[0037] Furthermore, the target image extraction unit 44 may extract target images from the internet, not limited to the social networking services (SNS) used by the user, of people who resemble the user and exhibit the facial expressions desired by the user. In other words, it may extract target images of other people whose facial features resemble the user's own. This allows for the extraction of target images of other people with faces almost identical to the user's, making it possible to provide appropriate target images for facial expression training even if the user has few images posted or saved on SNS. Additionally, there is the advantage that using images of other people who resemble the user is easier to project with an ideal image of how one wants to look than using images of one's own face.

[0038] The target image selection unit 45 selects a target image from the target images, taking into consideration third-party evaluations, and sends it to the user terminal 2. Third-party evaluations include, for example, the number of views, the number of likes, and the engagement rate. The number of views is the number of times the posted image has been viewed on SNS, and the number of likes is the number of reactions indicating empathy, such as "likes," given to the posted image. Reactions include not only those indicating empathy, such as "likes," but also "bad" reactions indicating undesirability or low quality, comments on the posted image, and reposts that quote the posted image. The engagement rate is an indicator that measures how many reactions there were to the posted image, and is calculated as follows, for example, "number of reactions to the posted image ÷ number of views of the posted image × 100".

[0039] The target image selection unit 45 takes into account third-party evaluations and, for example, if the user's desired expression is a "smile," it selects the target image that receives the most empathetic reactions, such as "like," and sets it as the target image. On the other hand, if the user's desired expression is an "angry face," it selects the target image that receives the most undesirable reactions, such as "bad," and sets it as the target image. The target image selection unit 45 may simply select the target image with the most reactions, or it may prioritize the quality of the reactions and select the target image that receives the most of a specific type of reaction. It may also consider multiple reactions in combination.

[0040] The target image selection unit 45 can arbitrarily set which third-party evaluation reaction it considers, according to the user's desired facial expression. Furthermore, the third-party evaluation can be calculated as a numerical value. For example, the target image selection unit 45 calculates a numerical value indicating the third-party evaluation based on one or more of the following: the number of views, the number of likes, the number of comments, the number of quotes, and the engagement rate of the target image.

[0041] The target image selection unit 45 may select more than one target image. If multiple target images are selected, the user may display all of the target images and perform training, or they may use the user terminal 2 to perform a predetermined operation to select and display one of the target images and perform training.

[0042] The target image selection unit 45 transmits and displays the target image to the user terminal 2. Figure 5 is an example of a display screen including the target image. The target image selection unit 45 creates a display screen having a real-time image area 50 and a target image area 51, as shown in Figure 5, and transmits it to the user terminal 2. The real-time image area 50 is the area that displays the real-time image of the user's face captured by the imaging unit 27 of the user terminal 2. The target image area 51 is the area that displays the selected target image. The user compares their real-time face image with the target image on the display screen shown on the user terminal 2 and trains their facial expressions to get closer to the target image.

[0043] In the above configuration, the input information acquisition unit 42, feature extraction unit 43, target image extraction unit 44, and target image selection unit 45 of the server 1 are examples of the input information acquisition means, feature extraction means, target image extraction means, and target image selection means of the present disclosure, respectively.

[0044] (Image selection process) Next, we will explain the image selection process performed by Server 1. Figure 6 is a flowchart showing an example of the image selection process performed by Server 1. This process is achieved by the processor 12 shown in Figure 2 executing a pre-prepared program.

[0045] First, Server 1 obtains input information from User Terminal 2 (Step S101). Next, Server 1 obtains a facial image of the user undergoing facial expression training from User Terminal 2 (Step S102). Next, Server 1 extracts features from the user's facial image to identify the user's face (Step S103).

[0046] Server 1 extracts target images from the user's terminal device and the internet, including social networking services (SNS), based on the feature data and input information (step S104). Next, Server 1 selects a target image from the target images based on third-party evaluations of the target images (step S105). Next, Server 1 creates a display screen containing the target image and sends screen information related to the display screen to User Terminal 2 (step S106). User Terminal 2, having received the screen information, displays the display screen containing the target image. Thus, the image selection process is completed.

[0047] According to this facial expression support system 100, Server 1 can provide users undergoing facial expression training with appropriate target images that take into account third-party evaluations. In other words, Server 1 can support the user's facial expression training by selecting appropriate target images. This allows users to train their facial expressions not with general target images, but with target images that are evaluated as desirable from a third-party perspective by those around them—that is, target images of their ideal facial expressions as judged by others. Furthermore, by using their own face image or a face image of someone similar to themselves as the target image, rather than a general target image, users can perform effective facial expression training.

[0048] [First variation] In the above embodiment, the input information includes text and images that represent the facial expression desired by the user, but this disclosure is not limited to this and may also include conditions for the target image. Conditions for the target image include, for example, conditions related to the date and time the target image was taken or posted, such as "the date and time the face image was taken is within the last year." Based on this, the target image extraction unit 44 can extract carefully selected target images from the internet according to the conditions, based on the feature quantities and input information.

[0049] [Second variation] In the above embodiment, the target image extraction unit 44 may extract facial images of other people who resemble the user from the internet as target images, based on the feature quantities and input information. In this case, if there are multiple people who resemble the user, the target image extraction unit 44 will prioritize selecting facial images of people with whom the user has interacted frequently on social networking services (SNS) or other platforms. The frequency of interaction is determined by the target image extraction unit 44 based on the SNS interaction history, for example, whether the person is a follower or whether there have been exchanges of comments or messages. Alternatively, the target image extraction unit 44 may prioritize selecting facial images of people who appear in many photos together with the user, rather than solely based on the frequency of interaction.

[0050] According to this, the target image extraction unit 44 can efficiently search for target images from the internet, focusing on close individuals with whom the user has many followers or exchanges messages, i.e., people they know well. By using the face images of close individuals as the target images, users can practice facial expressions in a familiar and comfortable way.

[0051] [Third variation] Server 1 may use a text emotion recognition AI (Artificial Intelligence) that infers emotions from input text. In this case, for example, the input information acquisition unit 42 inputs text indicating the facial expression desired by the user into the text emotion recognition AI, thereby recognizing the emotion of the facial expression desired by the user. As a result, the target image extraction unit 44 can extract target images by considering not only the text and images indicating the facial expression desired by the user, but also the emotion associated with that facial expression.

[0052] Furthermore, the target image extraction unit 44 recognizes the emotion of a comment by inputting a comment describing the face image from a social networking service where the face image has been posted into a text emotion recognition AI. As a result, the target image extraction unit 44 can extract a target image by considering the emotion of the comment describing the face image. Specifically, the target image extraction unit 44 prioritizes extracting target images from among the posted face images, based on the feature quantities and input information, in which the emotion of the comment matches the emotion of the facial expression desired by the user.

[0053] [Fourth variation] In the above embodiment, the user uses user terminal 2, but this disclosure is not limited thereto, and the user may use a user terminal that has the functionality of server 1. In this case, the user terminal can perform the image selection process that was performed by server 1, select the optimal target image for the user to perform facial expression training, and output it.

[0054] [Second Embodiment] Figure 7 is a block diagram showing an example of the functional configuration of the facial expression support device in this disclosure. The facial expression support device 90 comprises a feature extraction means 91, a target image extraction means 92, and a target image selection means 93.

[0055] Figure 8 is a flowchart illustrating an example of processing by the facial expression support device 90. The feature extraction means 91 extracts features from the user's face image to identify the user's face (step S201). The target image extraction means 92 extracts a face image with the desired expression as a target image from the terminal device used by the user and the social networking service (SNS) used by the user, based on the features (step S202). The target image selection means 93 selects and outputs a target image from among the target images based on a third-party evaluation of the target images (step S203).

[0056] In addition, some or all of the above embodiments (including modifications, the same applies hereinafter) may also be described as follows, but are not limited to the following.

[0057] (Note 1) A feature extraction means for extracting features from a user's facial image to identify the user's face, Based on the aforementioned features, a target image extraction means extracts a facial image with the desired expression from the terminal device used by the user and the social networking service used by the user as the target image. A target image selection means selects and outputs a target image from among the target images based on a third-party evaluation of the target image, A facial expression support device equipped with the following features.

[0058] (Note 2) It is equipped with an input information acquisition means that acquires input information indicating the desired facial expression, The aforementioned target image extraction means is an expression support device according to Appendix 1, which extracts the target image based on the feature quantities and the input information.

[0059] (Note 3) The aforementioned input information includes one or more text and / or images representing the desired facial expression, as described in Appendix 2 of the facial expression support device.

[0060] (Note 4) The facial expression support device described in Appendix 3, wherein the target image extraction means uses a text emotion recognition AI that infers emotions from input text to infer one or more emotions from the text contained in the input information and the text written in the comments of the target image, and extracts the target image based on the feature quantities and the emotions of the text.

[0061] (Note 5) The aforementioned input information includes conditions regarding the date and time the target image was taken or posted, The aforementioned target image extraction means is the facial expression support device described in Appendix 2, which extracts a target image that matches the aforementioned conditions.

[0062] (Note 6) The facial expression support device described in Appendix 1, wherein the evaluation by the third party is calculated based on one or more of the following: the number of views, the number of likes, the number of comments, the number of quotes, and the engagement rate of the target image.

[0063] (Note 7) The facial expression support device described in Appendix 1, wherein the target image extraction means extracts, based on the feature quantities, a facial image of a person with a desired expression that closely resembles the user's facial features from the internet, as the target image.

[0064] (Note 8) The facial expression support device described in Appendix 7, wherein the target image extraction means prioritizes extracting target images of individuals who have interacted with the user frequently on the SNS, among those whose facial features are similar to those of the user.

[0065] (Note 9) A facial expression support method performed by a facial expression support device, From the user's facial image, feature quantities are extracted to identify the user's face. Based on the aforementioned features, facial images with the desired expression are extracted as target images from the terminal device used by the user and the social networking service used by the user. A facial expression support method that selects and outputs a target image from among the target images based on a third-party evaluation of the target image.

[0066] (Note 10) A program executed by a facial expression support device equipped with a computer, From the user's facial image, feature quantities are extracted to identify the user's face. Based on the aforementioned features, facial images with the desired expression are extracted as target images from the terminal device used by the user and the social networking service used by the user. A program that causes the computer to perform a process of selecting and outputting a target image from among the target images based on a third-party evaluation of the target images.

[0067] Furthermore, some or all of the configurations described in Appendices 2 to 8, which are dependent on Appendice 1 above, may also be dependent on Appendices 9 and 10 in the same way as in Appendices 2 to 8. Moreover, not limited to Appendices 1, 8, and 9, some or all of the configurations described as appendices may also be dependent on various hardware, software, various recording means for recording software, or systems, without departing from the embodiments described above.

[0068] While the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure may be understood by those skilled in the art within the scope of the present disclosure. That is, the present disclosure includes the entire disclosure, including the claims, and of course, various modifications and alterations that those skilled in the art may make in accordance with the technical idea. [Explanation of Symbols]

[0069] 1 server 2 User terminals 11, 21 Interfaces 12, 22 processors 13, 23 memory 14, 24 Recording media 15, 25 Display section 16, 26 Input section 27 Imaging Unit 41. Face image acquisition unit 42 Input Information Acquisition Unit 43 Feature Extraction Unit 44 Target Image Extraction Unit 45 Target Image Selection Section 100 Facial Expression Support Systems

Claims

1. A feature extraction means for extracting features from a user's facial image to identify the user's face, Based on the aforementioned feature quantities, a target image extraction means extracts a facial image with the desired expression from the terminal device used by the user and the SNS used by the user as the target image. A target image selection means selects and outputs a target image from among the target images based on a third-party evaluation of the target image, A facial expression support device equipped with the following features.

2. It is equipped with an input information acquisition means that acquires input information indicating the desired facial expression, The facial expression support device according to claim 1, wherein the target image extraction means extracts the target image based on the feature quantities and the input information.

3. The facial expression support device according to claim 2, wherein the input information includes one or more text and images that indicate a desired facial expression.

4. The facial expression support device according to claim 3, wherein the target image extraction means uses a text emotion recognition AI that infers emotions from input text to infer one or more emotions from the text included in the input information and the text written in the comments of the target image, and extracts the target image based on the feature quantities and the emotions of the text.

5. The aforementioned input information includes conditions regarding the date and time the target image was taken or posted, The facial expression support device according to claim 2, wherein the target image extraction means extracts a target image that matches the above conditions.

6. The facial expression support device according to claim 1, wherein the evaluation by the third party is calculated based on one or more of the number of views, likes, comments, citations, and engagement rate of the target image.

7. The facial expression support device according to claim 1, wherein the target image extraction means extracts a facial image of a person with a desired expression that closely resembles the facial features of the user, from the internet, based on the feature quantities.

8. The facial expression support device according to claim 7, wherein the target image extraction means prioritizes extracting target images of individuals who have interacted with the user frequently on the SNS, among individuals whose facial features are similar to those of the user.

9. A facial expression support method performed by a facial expression support device, From the user's facial image, feature quantities are extracted to identify the user's face. Based on the aforementioned features, facial images with the desired expression are extracted as target images from the terminal device used by the user and the social networking service (SNS) used by the user. A facial expression support method that selects and outputs a target image from among the target images based on a third-party evaluation of the target image.

10. A program executed by a facial expression support device equipped with a computer, From the user's facial image, feature quantities are extracted to identify the user's face. Based on the aforementioned features, facial images with the desired expression are extracted as target images from the terminal device used by the user and the social networking service (SNS) used by the user. A program that causes the computer to perform a process of selecting and outputting a target image from among the target images based on a third-party evaluation of the target images.

Images