Outfit proposal device, outfit proposal method, and outfit proposal program

The clothing suggestion device addresses the lack of diversity in outfit suggestions by learning user-specific clothing types and preferences, offering personalized and varied outfit recommendations with enhanced user engagement.

JP2024163791AActive Publication Date: 2024-11-22REPLUS CO LTD

Patent Information

Application Number
JP2023079672
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-22
Estimated Expiration
2043-05-12

AI Technical Summary

Technical Problem

Existing outfit suggestion systems lack diversity in clothing recommendations, as they uniquely associate user facial features with specific clothing items, leading to a lack of variety in suggested outfits.

Method used

A clothing suggestion device that learns a correspondence between face images and clothing types using a trained model, identifies suitable clothing types based on facial features, and generates personalized outfit suggestions considering user preferences and store information.

Benefits of technology

The device provides diverse and personalized clothing recommendations, increasing user satisfaction by suggesting outfits that suit various users and align with their tastes, and includes features like beautification processing and store information output.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024163791000001_ABST
    Figure 2024163791000001_ABST
Patent Text Reader

Abstract

To provide an outfit proposal device that can propose an outfit suiting a user.SOLUTION: An outfit proposal device comprises: a storage unit which stores a learned model which has learned a correspondence relationship between a face image of a person and type information indicating one or more types of outfit suiting the person in the face image; a reception unit which receives input of a face image of a target user; a determination unit which determines type information on an outfit suiting the user using the face image received by the reception unit and the learned model; and an output unit which outputs the type information determined by the determination unit.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a clothing suggestion device, a clothing suggestion method, and a clothing suggestion program that can suggest clothing that suits a user based on a facial image of the user. [Background technology]

[0002] Conventionally, a user purchases and wears clothes that he or she thinks suit him or her according to his or her preferences. However, there are cases where the clothes that the user chooses do not necessarily suit the user. In this regard, Patent Document 1 discloses a fashion advising system that uses a face-product database that combines clothing products with a facial feature ID indicating facial features to provide fashion advice information that suits the user of the facial features of an input facial image. Similarly, Patent Document 2 discloses an information processing system that uses information that associates products with face types to identify the face type of a facial image captured by a camera and identify clothing that suits the user of the face. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-108287 A [Patent Document 2] JP 2022-173137 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned Patent Documents 1 and 2, because a user's facial features are uniquely associated with clothing, the clothing identified as suiting the user by Patent Documents 1 and 2 is always the same, resulting in a problem of a lack of variety in the clothing suggested.

[0005] The present invention has been made in consideration of the above problems, and has an object to provide a clothing suggestion device that can suggest clothing that suits a wide variety of users. [Means for solving the problem]

[0006] A clothing suggestion device according to one embodiment of the present invention includes a memory unit that stores a trained model that has learned the correspondence between a person's facial image and type information indicating one or more design types that suit the person in the facial image, a reception unit that receives an input of a facial image of a target user, and an identification unit that uses the facial image received by the reception unit and the trained model to identify clothing type information that suits the user.

[0007] In addition, in the above-mentioned clothing suggestion device, the memory unit may further store correspondence information that associates clothing with type information, and may be equipped with a suggestion unit that suggests clothing that suits the user based on the type information and correspondence information identified by the identification unit, and an output unit that outputs information about the clothing suggested by the suggestion unit.

[0008] In addition, in the above-mentioned clothing suggestion device, the reception unit may further include a generation unit that receives a plurality of full-body images showing a whole-body image of the user and generates, based on the full-body image, a wearing image showing the user wearing the clothing suggested by the suggestion unit, and the output unit may output the wearing image as information about the clothing suggested by the suggestion unit.

[0009] In the clothing suggestion device, the generation unit may generate a dressing image that has been subjected to a beautification process for beautifying the user.

[0010] In addition, in the above-mentioned clothing suggestion device, the clothing suggestion device may further include an acquisition unit that acquires preference information indicating the user's preferences, and the suggestion unit may suggest clothing that suits the user's preferences from among clothing identified based on the type information and the corresponding information.

[0011] In addition, in the above-mentioned clothing suggestion device, the memory unit may store information about retailers that sell clothing, an input unit may receive specific input from the user regarding the clothing suggested by the suggestion unit, and an output unit may output information about the retailer corresponding to the clothing when the specific input is received.

[0012] The clothing suggestion device may further include an output section that outputs type information.

[0013] In addition, in the above-mentioned clothing suggestion device, the identification unit may identify multiple pieces of clothing type information that suit the user and identify the degree of suitability for each type of information, and the output unit may output a heat map based on the type information and degree identified by the identification unit.

[0014] In addition, a clothing suggestion method according to one embodiment of the present invention executes a storage step in which a computer stores a trained model that has learned the correspondence between a person's facial image and type information indicating one or more design types that suit the person in the facial image, a reception step in which an input of a facial image of a target user is received, a determination step in which the facial image received in the reception step and the trained model are used to identify type information of clothing that suits the user, and an output step in which the type information identified in the determination step is output.

[0015] In addition, a clothing suggestion program according to one embodiment of the present invention provides a computer with a memory function for storing a trained model that has learned the correspondence between a person's facial image and type information indicating one or more design types that suit the person in the facial image, a reception function for accepting input of a facial image of a target user, a determination function for identifying type information of clothing that suits the user using the facial image accepted by the reception function and the trained model, and an output function for outputting the type information identified by the determination function. Effect of the Invention

[0016] The clothing suggestion device according to the present disclosure can first identify the type of clothing that suits the user, and then, for example, suggest a variety of types of clothing that suit the user based on the type, or suggest clothing that suits the user. [Brief description of the drawings]

[0017] [Figure 1] 1 is a system diagram showing an example of a system configuration of a clothing suggestion system. [Diagram 2] 1 is a block diagram showing an example of the configuration of a clothing suggestion device. [Diagram 3] FIG. 13 is a diagram showing an example of a map of clothing types. [Figure 4] (a) is an example of an input face image, and (b) is an example of an input full-body image. [Diagram 5] 13 is an example of a heat map showing identification information of clothes that suit a user. [Figure 6] This is an example of an output of a user wearing clothes that suit him / her. [Figure 7] 11 is a first flowchart showing an example of a process for outputting identification information of clothes that suit a user. [Figure 8] 13 is a second flowchart showing an example of a process for outputting a state in which the user is dressed in clothes that suit the user. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a clothing suggestion device, a clothing suggestion method, and a clothing suggestion program according to the present invention will be described in detail with reference to the drawings.

[0019] <Embodiment> Hereinafter, a clothing suggestion device according to the present invention will be described in detail with reference to the drawings.

[0020] 1 is a system diagram showing an example of the configuration of a communication system including a clothing suggestion device 100. Clothing suggestion device 100 is connected via network 40 to an external device, for example, an information processing terminal 200 of a user, so as to be able to communicate with the external device.

[0021] As shown in FIG. 1, a user accesses the clothing suggestion device 100 using his / her own information processing terminal 200. The user transmits a captured image of the user's face and whole body from his / her own information processing terminal 200 to the clothing suggestion device 100. Based on the received face image, the clothing suggestion device 100 identifies a type of clothing that suits the user, and identifies clothing that fits the identified type. The clothing suggestion device 100 then transmits type information indicating the identified type of clothing that suits the user, or a photograph of the user wearing the clothing that suits the user, or both, to the information processing terminal 200. This allows the user to recognize the type of clothing and clothing that suits him / her.

[0022] In addition, the clothing suggestion device 100 may transmit information or a homepage of a store 30 that sells clothing that matches the identified clothing type, or a URL of an EC site, to the information processing terminal 200, and in response, the information processing terminal 200 may access the site information of the store 30 and purchase the clothing.

[0023] The network 40 is a network for connecting various devices to each other, and is, for example, a wireless network or a wired network. Specifically, the network is a wireless LAN (WLAN), a wide area network (WAN), integrated service digital networks (ISDNs), wireless LANs, long term evolution (LTE), LTE-Advanced, fourth generation (4G), fifth generation (5G), sixth generation (6G), code division multiple access (CDMA), WCDMA (registered trademark), Ethernet (registered trademark), etc. The network is not limited to these examples, and may be any network, such as a public switched telephone network (PSTN), Bluetooth (registered trademark), Bluetooth Low Energy, optical fiber, or a satellite communication network. The network may also include a plurality of different networks that combine these examples.

[0024] The clothing suggestion device 100 will be described in detail below.

[0025] <Configuration> FIG. 2 is a block diagram showing an example of the configuration of clothing suggestion device 100. Clothing suggestion device 100 is an information processing device (computer system) that can accept input of a face image of a user, identify a type of clothing that suits the user with the face shape indicated by the face image, and provide the user with the information. Clothing suggestion device 100 may also be an information processing device that provides information on clothing that matches the identified type, and the clothing information may be a photo of only the clothing, but in this embodiment, an image of the user wearing the clothing is provided as clothing information. Clothing suggestion device 100 may be realized as a server device that provides information in response to access from information processing terminals of multiple users, but may also be realized by a PC, tablet terminal, or the like.

[0026] As shown in FIG. 2, the clothing suggestion device 100 includes a communication section 110, an input section 120, an output section 130, a storage section 140, and a control section 150.

[0027] The communication unit 110 is a communication interface that communicates with the user's information processing terminal 200 via the network 40. The communication unit 110 transmits the received information to the control unit 150. The communication unit 110 also transmits the specified information to a specified destination according to an instruction from the control unit 150. For example, the communication unit 110 receives a face image and a whole-body image of the user transmitted from the user's information processing terminal 200, and transmits them to the control unit 150. The communication unit 110 also transmits information indicating a type of clothing that suits the user and information about clothing that suits the user to the user's information processing terminal 200 according to an instruction from the control unit 150.

[0028] Input unit 120 accepts input from a user (e.g., an operator) of clothing suggestion device 100 and transmits the accepted input content to control unit 150. Input unit 120 may be realized by a keyboard or mouse of clothing suggestion device 100, or may be realized by a connection port of a flash memory or the like. As an example, input unit 120 may transmit to control unit 150 a face image and a whole-body image of the user stored in a connected flash memory.

[0029] Output unit 130 outputs specified information in accordance with instructions from control unit 150. Output by output unit 130 is realized, for example, by outputting characters or images on a monitor connected to clothing suggestion device 100, outputting audio from a speaker connected to clothing suggestion device 100, or outputting to an external device by communication via communication unit 110. As an example, output unit 130 may transmit a heat map indicating the types of clothing that suit the user to user's information processing terminal 200 via communication unit 110, or may transmit a composite photograph of the user wearing clothing that suits the user to user's information processing terminal 200.

[0030] The storage unit 140 stores various programs and data required for the operation of the clothing suggestion device 100. The storage unit 140 may be realized by, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc., but is not limited thereto. The storage unit 140 may store a program for identifying a type of clothing that suits the user and generating a heat map, or a program for suggesting clothing that suits the user. The storage unit 140 may also store a trained model 141 used to identify a type of clothing that suits the user, and may store clothing information 142 indicating actual clothing corresponding to various types of clothing as corresponding information. The storage unit 140 may also be realized by a cloud storage on the network 40 accessible by the clothing suggestion device 100.

[0031] The trained model 141 is for identifying a type of design that suits a user based on a face image of the user, and in this embodiment, is a trained model for identifying a type of clothing that suits the user, and is a model that inputs a face image captured from the front of the user and outputs the degree of suitability for each of the predetermined types of clothing. The trained model 141 may be a trained model that has learned information that associates information indicating a type of clothing that suits each of various user's face images with each other as teacher data. Alternatively, the trained model 141 may be a trained model that has learned information that associates information indicating a degree of suitability for each of the predetermined types of clothing with each of various user's face images with each other as teacher data. The trained model 141 is preferably a model that outputs multiple types of clothing that suit the user, and may be a model that outputs a predetermined number of types of clothing information in descending order of suitability, or may be a model that outputs the degree of suitability for all types. The trained model 141 may be a model generated by so-called machine learning or deep learning, and may be realized by a well-known neural network, support vector machine, naive Bayes, etc., but is not limited to these.

[0032] The clothing information 142 is information in which type information indicating a type of clothing is associated with information indicating the clothing, and is information that can identify clothing corresponding to the type of clothing indicated by the type information based on the type information. The clothing information 142 may store a photo or name of the clothing as information indicating the clothing, or may store an image of a model wearing the clothing. Furthermore, multiple type information may be associated with each piece of clothing.

[0033] Control unit 150 is a processor having the function of controlling each unit of clothing suggestion device 100. Control unit 150 uses various data stored in storage unit 140 and executes various programs to perform the functions that clothing suggestion device 100 should perform.

[0034] The control unit 150 functions as a receiving unit 151, a specifying unit 152, a proposing unit 153, and a generating unit 154.

[0035] The reception unit 151 receives an input of a face image of a user for whom a type of clothing or clothes is to be proposed. The reception unit 151 also receives an input of a whole-body image of the user. The reception unit 151 receives the face image or the whole-body image from the communication unit 110 or the input unit 120. The reception unit 151 transmits the received face image to the identification unit 152. The reception unit 151 also transmits the received whole-body image to the proposal unit 153 and the generation unit 154. The reception unit 151 receives, as an example, a face image 400 and a whole-body image 410 as shown in Figs. 4(a) and 4(b). Note that it is preferable that the whole body image 410 shows the whole body of the user as much as possible, but as shown in Fig. 4(b), a part (for example, the feet) may be missing. It is also preferable that there are a plurality of whole-body images taken from different angles, and it is even better if there are images of different poses.

[0036] The identification unit 152 identifies a type of clothing that suits the user based on the face image transmitted from the reception unit 151. The identification unit 152 inputs the transmitted face image to the trained model 141 to identify a type of clothing that suits the user of the face image. The identification unit 152 generates type information indicating a type of clothing that suits the user identified by the trained model 141. The type information may be a character string indicating the type of clothing or information indicating a degree (numerical value) of conformity with the various types of information, but in this embodiment, the type information is output to the output unit 130 as an identifiable heat map. That is, the identification unit 152 may generate a heat map indicating which type suits the user on a map on which information indicating the types of clothing is distributed as type information, and output it to the output unit 130 (transmit it to the information processing terminal 200 via the communication unit 110).

[0037] Here, a map 300 of type information showing the type of clothing will be described. FIG. 3 is a map showing the type of clothing proposed to the user by the clothing suggestion device 100 according to this embodiment, and in this embodiment, 22 types of clothing are specified as types of clothing: "cute idol type", "clear sporty type", "soft casual calm type", "casual popular type", "feminine healing type", "sporty athletic type", "dynamic bold type", "ethnic ethnic type", "wild warrior type", "traditional detective type", "classic antique type", "dandy brother type", "romantic fantasy type", "natural organic type", "noble royal family type", "soft modern cool type", "gorgeous celebrity type", "hard modern space type", "elegant gorgeous aristocracy type", "soft elegant fairy type", "elegant Parisienne type", and "formal scholar type", and are arranged on the map 300 as shown in the figure. The map 300 shown in FIG. 3 is a map with feminine-masculine on the vertical axis and static-dynamic on the horizontal axis. In map 300 of Fig. 3, the higher you go, the more feminine the type of clothing, and the lower you go, the more flexible the type of clothing. Also, the further to the right you go on map 300, the more subdued the type of clothing, and the further to the left you go, the more active and mobile the type of clothing. Therefore, in map 300, the upper left is an objectively approachable type of clothing, the upper right is a sophisticated type of clothing, the lower left is a dynamic type of clothing, the lower right is a trustworthy type of clothing, and the closer to the center, the more natural the type of clothing.

[0038] Then, for the map 300, the identification unit 152 may generate a heat map 500 as shown in FIG. 5 as an example, so that the clothing type identified as suitable for the user has a stronger color or a more noticeable color, and output the heat map 500 to the output unit 130. In the example of the heat map 500 shown in FIG. 5, as shown by hatching 310 and 320, it is shown that the user has a strong aptitude for "soft modern cool" and "elegant gorgeous aristocracy" (suits the user). In addition, it can be seen that the "noble imperial family", "natural organic", "gorgeous celebrity", and "formal scholar" are also identified as clothing types that suit the user, although they suit the user less well than the "soft modern cool" and "elegant gorgeous aristocracy". In this way, the identification unit 152 can identify the type of clothing that suits the user based on the user's face image, and can output the information. Therefore, the specifying unit 152 can specify a plurality of type information items as types of clothing that suit the user, and can provide the user with a wide variety of clothing suggestions.

[0039] The identification unit 152 transmits the identified clothing type to the suggestion unit 153 .

[0040] The suggestion unit 153 identifies clothing corresponding to the clothing type identified by the identification unit 152, with reference to the clothing information 142. Then, the suggestion unit 153 instructs the output unit 130 to output the identified clothing information (to transmit it to the user's information processing terminal 200 via the communication unit 110). This allows the user to recognize clothing that suits him or her. The clothing information suggested to the user by the suggestion unit 153 may be a wearing image generated by the generation unit 154 of the user wearing the clothing.

[0041] The generation unit 154 generates a wearing image of the user wearing the clothes specified by the proposal unit 153 based on the clothes specified by the proposal unit 153 and the whole-body image accepted from the acceptance unit 151, and transmits the generated image to the proposal unit 153. As an example, the generation unit 154 specifies a pair of model images wearing the clothes stored in the clothing information 142 and the accepted whole-body image that have similar poses, and generates a wearing image by processing the specified model image to give a natural impression while synthesizing the user's face image.

[0042] The generation unit 154 may perform beautification processing to beautify the user as the processing, and may perform various processing to improve the user's appearance. The processing here may be processing such as applying makeup that suits the user, whitening the user's skin, removing wrinkles, making the user slimmer or smarter, adding accessories that suit the user, making the eyes double, lengthening the eyelashes, etc. For processing these images, various existing algorithms (for example, photo apps) can be used. FIG. 6 shows an example of a wearing image in which the user is wearing the clothes specified by the suggestion unit 153 based on the user's images shown in FIGS. 4(a) and 4(b), and an example of beautification processing is performed.

[0043] The generation unit 154 transmits the generated dressing image of the user wearing clothes that suit the user to the suggestion unit 153.

[0044] The above is an example of the configuration of the clothing suggestion device 100. Note that the user's information processing terminal 200 is similar to a general smartphone, mobile phone, notebook PC, or tablet terminal, and therefore a detailed description thereof will be omitted.

[0045] <Operation> Next, a description will be given of an example of the operation of the clothing suggestion device 100. Fig. 7 is a first flowchart showing an example of the operation of the clothing suggestion device 100 to output to a user information on the type of clothing that suits the user.

[0046] 7, the receiving unit 151 of the control unit 150 of the clothing suggestion device 100 receives an input of a face image of a user (step S701). The receiving unit 151 transmits the received face image to the identifying unit 152.

[0047] When the identification unit 152 receives the face image of the user from the reception unit 151, the identification unit 152 identifies a type of clothing that suits the user based on the face image. That is, the identification unit 152 inputs the transmitted face image to the trained model 141. Then, the identification unit 152 identifies a type of clothing that suits the user based on information indicating a degree of suitability for the clothing type information output from the trained model 141. That is, the identification unit 152 identifies a type that suits the clothing type information to a high degree (step S702).

[0048] The identification unit 152 creates a heat map (see FIG. 5 as an example) indicating the type of clothing that suits the user based on the identified type (step S703).

[0049] Then, the suggestion unit 153 causes the output unit 130 to output the created heat map as type information indicating the type of clothing that suits the user. The output unit 130 transmits the specified type information (heat map) to the information processing terminal 200 via the communication unit 110 (step S704), and ends the process.

[0050] 7, the clothing suggestion device 100 can present to the user the type of clothing that suits the user. Therefore, the user can recognize the type of clothing that suits him / her, and can use it as a reference for future clothing purchases, for example. Note that the identification unit 152 may output a character string indicating the identified type of clothing, instead of a heat map.

[0051] 8 is a second flowchart showing an example of an operation of outputting information on clothes that suit a user, to the user, by the clothing suggestion device 100. Note that in FIG. 8, the processes in steps S701 and S702 are similar to the processes with the same reference numerals shown in FIG.

[0052] 8, the receiving unit 151 of the control unit 150 of the clothing suggestion device 100 receives an input of a face image of the user (step S701). The receiving unit 151 transmits the received face image to the identifying unit 152.

[0053] When the identification unit 152 receives the face image of the user from the reception unit 151, the identification unit 152 identifies a type of clothing that suits the user based on the face image. That is, the identification unit 152 inputs the transmitted face image to the trained model 141. Then, the identification unit 152 identifies a type of clothing that suits the user based on information indicating a degree of suitability for the clothing type information output from the trained model 141. That is, the identification unit 152 identifies a type that is highly suitable for the clothing type information (step S702). The identification unit 152 transmits the identified clothing type information to the suggestion unit 153.

[0054] The suggestion unit 153 identifies clothes that suit the user based on the type information transmitted from the identification unit 152 (step S803). That is, the suggestion unit 153 identifies clothes associated with the transmitted type information by referring to the clothing information 142. The suggestion unit 153 may identify multiple clothes from the clothing information 142, or may identify only one that is assumed to suit the user best. In addition, when multiple clothes are proposed, a predetermined number may be identified in order of suitability. As an example, the suitability referred to here may be determined as a degree of suitability when there is multiple type information of clothes that suit the user and multiple type information are associated with the clothes, with a large number of matching pieces being the clothes that suit the user. The suggestion unit 153 transmits information on the identified clothes to the generation unit 154.

[0055] The receiving unit 151 receives an input of a whole-body image of the user (step S804). The receiving unit 151 transmits the received whole-body image to the generating unit 154.

[0056] The generating unit 154 generates a wearing image showing the user wearing the clothes based on the transmitted whole-body image and the information on the clothes specified by the proposing unit 153 (step S805). At this time, the generating unit 154 may generate a wearing image that has been subjected to beautification processing to beautify the user. The generating unit 154 transmits the generated wearing image to the proposing unit 153.

[0057] Then, the suggestion unit 153 instructs the output unit 130 to output the wearing image transmitted from the generation unit 154. Then, the output unit 130 transmits the transmitted wearing image to the information processing terminal 200 of the user via the communication unit 110 (step S806), and ends the process.

[0058] In this way, the clothing suggestion device 100 can show the user what kind of atmosphere the user will have when wearing clothing that suits the user. This can increase the user's motivation to purchase the clothing. Note that, although the timing for accepting the input of the face image and the input of the whole body image (steps S701 and S804) is separate in FIG. 8, these may be simultaneous.

[0059] <Summary> According to the clothing suggestion device 100 of this embodiment, it is possible to output information on the type of clothing that suits the user. By providing information indicating the type of clothing rather than the clothing itself, it is possible to provide a variety of clothing that suits the user. In addition, it is also possible to suggest the clothing that suits the user, and by providing the user with an image of the user wearing the clothing, it is possible to increase the user's purchasing motivation. In addition, by performing a beautification process on the wearing image, it is also possible to further increase the user's purchasing motivation.

[0060] <Supplementary Information> The clothing suggestion device 100 according to the above embodiment is not limited to the aspects shown in the above embodiment. Various modifications will be described below.

[0061] (1) In the above embodiment, the clothing suggestion device 100 identifies a type of clothing that suits a user based on the user's face, and suggests clothes according to that type. However, the user naturally has preferences, and it is a separate matter whether the suggested clothes match the user's preferences. Therefore, the clothing suggestion device 100 may be further configured to suggest clothes that suit the user and may also match the user's tastes.

[0062] For this purpose, the control unit 150 of the clothing suggestion device 100 may include an acquisition unit that acquires preference information indicating the user's preferences. For example, the acquisition unit may acquire the preference information by inputting information indicating the target user's preferences via the input unit 120 by an operator of the clothing suggestion device 100, or may acquire preference information input by the user himself / herself from the user's information processing terminal via the communication unit 110 by communication, or may specify the user's preference information by referring to the user's purchase history on an EC site or the like when the user has permission, or may analyze and acquire the user's preferences by analyzing posts on the blog using morphological analysis or the like when the user has a blog.

[0063] The preference information may basically be information indicating the user's preference for clothing, such as color preference, clothing material preference, clothing shape preference, or clothing type preference (e.g., skirt preference, pants preference, etc.). The preference information may also be information indicating (expressing) the overall atmosphere of the preferred clothing (e.g., formal, casual, feminine, cute, stylish, dandy, etc.).

[0064] Each piece of clothing registered in the clothing information 142 is associated with information indicating the characteristics of the clothing as metadata. The metadata may be the color, type, shape characteristics, or mood of the clothing.

[0065] The suggestion unit 153 may further suggest clothes that match the user's preference information, i.e., clothes that have metadata corresponding to at least one of the user's preference information, from among the clothes identified based on the user's face. At this time, the suggestion unit 153 may give a high priority to clothes that have a lot of metadata that match the user's preference information, and instruct the output unit 130 to preferentially display a composite image of the user wearing the clothes. In addition, the suggestion unit 153 may present clothes that are determined to suit the user even if they do not match the user's preferences, with an explanation such as, for example, "This kind of outfit may not be to your taste, but I think that this kind of outfit would look good on you."

[0066] In this way, the clothing suggestion device 100 can suggest clothing that not only suits the user, but also is likely to match the user's preferences in addition to looking good on the user, thereby further increasing the user's desire to purchase clothing.

[0067] (2) In the above embodiment, the clothing suggestion device 100 outputs type information indicating the type of clothing to the user and outputs an image of the user wearing the clothing that suits the user. However, the clothing suggestion device 100 may also introduce the user to a store where the clothing can be purchased or provide information on an EC site.

[0068] To achieve this, clothing information 142 may also include, for each piece of clothing, information about the store that sells the clothing (store name, contact information, location, etc.) and the URL of the e-commerce site that sells the clothing.

[0069] Then, for example, when a user makes a predetermined input (such as a touch input on the clothing) in response to an image of the user wearing clothing that suits the user, the clothing suggestion device 100 may output information such as the location of a store that sells the clothing that is close to the address information input by the user. Also, the clothing suggestion device 100 may be configured to display the URL of an EC site that sells the clothing, instead of information such as the store location, or to directly access the EC site of the URL.

[0070] In this way, if a user likes an item of clothing presented by the clothing suggestion device 100, the user can be presented with an environment in which the user can immediately purchase the clothing, thereby providing the user with a highly convenient clothing suggestion device 100.

[0071] (3) In the above embodiment, the clothing suggestion device 100 suggests clothes that suit the user. However, the clothing suggestion device 100 may be configured as a suggestion device that suggests things other than the clothes. In the above embodiment, the type information is described as specifying the type of clothes that suit the user, but the type information can also be said to be information that specifies the type of design that suits the user, and can be used to suggest designs related to the user. The type information shown in the above embodiment can also be said to specify the atmosphere that suits the user, and can be used to suggest things related to the user.

[0072] As an example, the suggestion device may be a device that suggests a color that suits the user based on the user's face image. Specifically, the suggestion device uses information that associates type information with information indicating a color instead of the clothing information 142 as the corresponding information, and the suggestion unit specifies a color that corresponds to the type information specified by the specification unit 152. Then, the suggestion unit may output information indicating the specified color to the output unit 130 as a color that suits the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's face image and suggests a color that suits the user, and the user can use the suggested color as a reference when purchasing something, such as clothes or a car.

[0073] As another example, the suggestion device may be a device that suggests makeup that suits a user based on a facial image of the user. Specifically, the suggestion device uses, as the correspondence information, instead of the clothing information 142, correspondence information in which type information is associated with information indicating makeup, and the suggestion unit specifies makeup that corresponds to the type information specified by the specification unit 152. Then, the suggestion unit may cause the output unit 130 to output the specified information indicating makeup as a color that suits the user. In this case, the suggestion device is a device that accepts a face image of the user and suggests makeup that suits the user, and the user can see the face image with the makeup applied and use it as a reference for future makeup. In addition, at this time, the suggestion device may suggest a salon that can apply makeup that suits the user and is easy for the user to visit.

[0074] As another example, the suggestion device may be a device that proposes a hairstyle that suits the user based on the user's face image. Specifically, the suggestion device uses information that associates type information with information indicating a hairstyle instead of the clothing information 142 as the corresponding information, and the suggestion unit specifies a hairstyle that corresponds to the type information specified by the specification unit 152. Then, the suggestion unit may output information indicating the specified hairstyle to the output unit 130 as a hairstyle that suits the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's face image and proposes a hairstyle that suits the user, and the user can refer to the image of the user with the hairstyle for future hairstyles. In addition, at this time, the suggestion device may propose a hair salon that can give the user a hairstyle that suits the user and is easy for the user to visit.

[0075] As another example, the suggestion device may be a device that suggests nails that suit the user based on the user's face image. Specifically, the suggestion device uses information that associates type information with information indicating nails instead of the clothing information 142 as the corresponding information, and the suggestion unit specifies nails that correspond to the type information specified by the specification unit 152. Then, the suggestion unit may output the specified information indicating the nails to the output unit 130 as nails that suit the user. The trained model 141 may be a model that has learned the user's face image and nails that suit the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's face image and suggests nails that suit the user, and can be used as a reference for future nails. In addition, at this time, the suggestion device may suggest a nail salon that can perform nails that suit the user and is easy for the user to visit.

[0076] As another example, the suggestion device may be a device that suggests jewelry (rings, earrings, pierced earrings, necklaces, cuffs, etc.) and accessories (watches, ties, hair bands, bandanas, shoes, hats, etc.) that suit the user based on the user's face image. Specifically, the suggestion device uses information that associates type information with information indicating jewelry (or accessories) instead of clothing information 142 as the corresponding information, and the suggestion unit specifies jewelry (or accessories) that corresponds to the type information specified by the specification unit 152. Then, the suggestion unit may output information indicating the specified jewelry to the output unit 130 as jewelry (or accessories) that suit the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's face image and suggests jewelry and accessories that suit the user, and can be used as a reference for future purchases of jewelry and accessories.

[0077] As another example, the suggestion device may be a device that suggests an interior that suits the user based on the user's face image. As an example, the interior may include at least any of the interior items of the electric appliance, furniture, house, etc. (for example, wallpaper, wood, tiles, etc. used). Specifically, the suggestion device uses, as the corresponding information, information that associates type information with information indicating the interior, instead of the clothing information 142, and the suggestion unit specifies the interior that corresponds to the type information specified by the specification unit 152. Then, the suggestion unit may output the information indicating the specified interior to the output unit 130 as the interior that suits the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's face image and suggests an interior that suits the user, and can be used as a reference for future purchases of interior.

[0078] As another example, the suggestion device may be a device that suggests real estate that suits the user based on the user's face image. The real estate may be, for example, a house, an apartment, a condominium, a store, or a building or some kind of facility. Specifically, the suggestion device uses, as the corresponding information, information that associates type information with information indicating real estate, instead of the clothing information 142, and the suggestion unit identifies real estate that corresponds to the type information identified by the identification unit 152. Then, the suggestion unit may output information indicating the identified real estate to the output unit 130 as real estate that suits the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's face image and suggests real estate that suits the user, and can be used as a reference for future real estate purchases.

[0079] As another example, the suggestion device may be a device that proposes a service that suits the user based on the user's facial image. As an example, the service may be a travel plan of a travel agency. Specifically, the suggestion device uses information that associates type information with information indicating service content instead of clothing information 142 as the corresponding information, and the suggestion unit specifies the service content corresponding to the type information specified by the specification unit 152. Then, the suggestion unit may output information indicating the specified service content to the output unit 130 as a service that suits the user. Therefore, in this case, the suggestion device becomes a device that accepts the user's facial image and proposes service content that suits the user, and can be used as a reference for purchasing future service content.

[0080] As another example, the suggestion device may be a device that suggests a person who suits the user based on the user's face image. As described above, the type information may indicate an atmosphere that suits the user, and in the case of two people, a person who has a good atmosphere may be suggested. Specifically, the suggestion device uses information that associates type information with information indicating a person instead of the clothing information 142 as the correspondence information, and the suggestion unit specifies a person corresponding to the type information specified by the specification unit 152. Then, the suggestion unit may output information indicating the specified person to the output unit 130 as a person who suits the user. Therefore, in this case, the suggestion device is a device that accepts the user's face image and suggests a person who suits the user. Note that the person referred to here may be, for example, a teacher at a cram school, a teacher of extracurricular activities, a makeup artist, a manicurist, a designer of some kind, or a spouse.

[0081] In this way, by simply changing the correspondence information that associates the proposed target with each type indicated by the type information, the suggestion device can make various suggestions that suit the user. In addition, since it is only necessary to change the correspondence information, the labor required for building the system can be reduced.

[0082] (4) In the above embodiment, the clothing information 142 as the corresponding information is registered with actual clothing, and clothing that suits the user is proposed by the clothing proposal device 100 from among the actual clothing. However, the clothing proposed by the clothing proposal device 100 may be virtual clothing generated by the proposal unit. Specifically, a learning model is prepared by learning information that associates suitable clothing with each type indicated by the type information as training data. Then, by inputting type information identified by the identification unit into the learning model, clothing that suits the user is automatically generated, and an image of the user wearing the automatically generated clothing is generated and output. This allows, for example, the user to obtain a design for custom-made clothing, and may request the production of the clothing from a store or the like that undertakes the production of custom-made clothing, and the proposal device may provide guidance therefor.

[0083] In addition, the learning model may be a learning model that learns teacher data that associates clothes that suit the user with a heat map of type information that indicates clothes that suit the user, and in this case, the heat map is input. In this way, the suggestion device may suggest clothes that it has created itself.

[0084] (5) In the above embodiment, the receiving unit 151 receives a face image and a whole-body image of the user. However, the receiving unit 151 may receive only a whole-body image as long as the image shows the user's face from the front. In this case, the identifying unit 152 may trim the user's face image from the whole-body image and input the trimmed image to the trained model 141 as a face image to identify the type of clothing that suits the user.

[0085] (6) The clothing information 142 shown in the above embodiment may be updated as appropriate, for example, every time a new item is released, in which case photo information of the new item of clothing and information on the type of clothing may be registered in the clothing information 142. The registration may be performed by an operator of the clothing suggestion device 100, or a salesperson or designer at a store selling clothing may access the clothing suggestion device 100 and register the information. In this way, the clothing suggestion device 100 can always make suggestions that include the latest clothing, making it possible to realize clothing suggestions that the user using the clothing suggestion device 100 will not tire of.

[0086] Also, the clothing information 142 may be divided into a plurality of pieces according to the target of the clothing, for example. For example, it may be divided by season (spring, spring / summer, summer, autumn, winter, all seasons, etc.) or by target age (child, adult, senior, etc.). In other words, various types of clothing information 142 may be provided and stored in the storage unit 140. By configuring in this way, the clothing suggestion device 100 can give a sense of the season to the clothes it proposes and suggest clothes that are more appropriate to the user. To realize this configuration, the clothing suggestion device 100 may be configured to specify which clothing information to use based on not only a face image or a full-body image from the user, but also attribute information of the user (age, sex, etc.) and date and time information of the day of input. Also, which clothing information to use may be selected by the user.

[0087] (7) The clothing suggestion device 100 may be provided with a re-learning unit that updates the trained model 141 by re-learning a pair of a type of clothing that suits the user, as determined by the clothing suggestion device 100 itself, and the user's facial image input at that time, as new training data.

[0088] (8) In the above embodiment, an example has been shown in which a user accesses clothing suggestion device 100 from information processing terminal 200 and clothing suggestion device 100 suggests types of clothing and clothes that suit the user, but the functions realized by clothing suggestion device 100 may also be realized by a clothing suggestion app (application) or the like executed by information processing terminal 200. The clothing suggestion app may be realized as a standalone app that operates on information processing terminal 200 alone, or as a network app that communicates with and links to a server device such as clothing suggestion device 100 via the clothing suggestion app.

[0089] (9) When each functional unit of the clothing suggestion device 100 is realized by software, the clothing suggestion device 100 includes a CPU that executes instructions of a program that is software that realizes each function, a ROM (Read Only Memory) or storage device (these are referred to as "recording media") in which the program and various information are recorded so as to be readable by a computer (or CPU), and a RAM (Random Access Memory) in which the program is expanded. The object of the present invention is achieved by the computer (or CPU) reading and executing the program from the recording medium. That is, the clothing suggestion device 100 according to the present invention functions as each of the above-mentioned components by the CPU executing the program loaded on the RAM. As the recording medium, a "non-transient tangible medium", for example, a semiconductor memory, a programmable logic circuit, etc. can be used. The program may also be supplied to the computer via any transmission medium (such as a communication network or a broadcast wave) capable of transmitting the program. The present invention may also be realized in the form of an information signal embedded in a carrier wave in which the program is embodied by electronic transmission.

[0090] The above program may be implemented using, for example, a scripting language such as ActionScript, JavaScript (registered trademark), Python, or Ruby, an object-oriented programming language such as C language, C++, C#, Objective-C, Swift, or Java (registered trademark), or a markup language such as HTML5. Furthermore, the term "section, module, or unit" in the claims may be read as "means" or "circuit." For example, a communication section may be read as a communication means or a communication circuit.

[0091] Furthermore, the program of the present disclosure may be provided to the clothing suggestion device 100 via any transmission medium (such as a communication network or broadcast waves) capable of transmitting the program.

[0092] (10) The order and timing of each process described in the above embodiment may be changed as appropriate, provided that the same effects as those described in the above embodiment can be achieved.

[0093] (11) The configurations shown in the above embodiment and the configurations shown in the above modified examples may be combined as appropriate to achieve the purpose of suggesting items that suit the user. [Explanation of symbols]

[0094] 100 Clothes suggestion device 110 Communications Department 120 Input section 130 Output section 140 Storage section 141 trained models 142 Clothing information 150 Control section 151 Reception 152 Specific part 153 Proposal Department 154 Generation part

Claims

1. A storage unit that stores a trained model that has learned a correspondence relationship between a face image of a person and type information indicating one or more design types that suit the person in the face image; A reception unit that receives an input of a face image of a target user; An identification unit that identifies type information of clothing that suits the user using the face image accepted by the acceptance unit and the trained model; A clothing suggestion device comprising:

2. The storage unit further stores correspondence information that associates clothing with the type information, a suggestion unit that suggests clothes that suit the user based on the type information identified by the identification unit and the correspondence information; an output unit that outputs information about the clothing recommended by the recommendation unit; 2. The clothing suggestion device according to claim 1.

3. The receiving unit further receives a plurality of whole-body images showing a whole-body image of the user, a generator that generates a wearing image showing a state in which the user wears the clothing suggested by the suggestion unit based on the whole-body image, The output unit outputs the wearing image as information on the clothing proposed by the proposal unit.

3. The clothing suggestion device according to claim 2.

4. The generating unit generates a wearing image that has been beautified to beautify the user.

4. The clothing suggestion device according to claim 3.

5. The clothing suggestion device further includes: An acquisition unit that acquires preference information indicating the preferences of the user, The suggestion unit suggests clothes that match a preference of the user from among clothes identified based on the type information and the correspondence information.

3. The clothing suggestion device according to claim 2.

6. The storage unit stores information about a store that sells the clothing, an input unit that receives a predetermined input from the user regarding the clothing suggested by the suggestion unit; The output unit outputs information about the store corresponding to the clothing item when the predetermined input is received.

6. The clothing suggestion device according to claim 2, wherein the clothing suggestion device is a device for suggesting clothing to a user.

7. an output unit for outputting the type information 2. The clothing suggestion device according to claim 1.

8. The identification unit identifies a plurality of types of clothing information suitable for the user and identifies a degree of suitability for each type of clothing information, The output unit outputs a heat map based on the type information and the degree identified by the identification unit.

8. The clothing suggestion device according to claim 7.

9. The computer A storage step of storing a trained model that has learned a correspondence relationship between a face image of a person and type information indicating one or more design types that suit the person of the face image; A receiving step of receiving an input of a face image of a target user; A specification step of specifying information on the type of clothing that suits the user using the face image accepted in the acceptance step and the trained model; A clothing suggestion method that implements the above.

10. On the computer, A memory function for storing a trained model that has learned a correspondence between a face image of a person and type information indicating one or more design types that suit the person in the face image; A reception function for receiving an input of a face image of a target user; A specification function that specifies type information of clothing suitable for the user using the face image accepted by the reception function and the trained model; A clothing suggestion program that makes this a reality.

Citation Information

Patent Citations

  • Information processor, cloth proposing method and cloth proposing program

    JP2019071027A

  • Information processing device, information processing system, learning device, learned estimation model, and method for collecting data for learning

    JP2020071811A

  • Dress proposal device, dress proposal method, and program

    JP2020107084A

  • Fashion type diagnostic system and fashion type diagnostic method

    JP2020166454A

  • Dress learning system, dress evaluation system, dress learning evaluation system, electron mirror, dress learning method, dress evaluation method, and program

    JP2021009517A

Cited By

  • system

    JP2026155743A