WO2023090601A1

WO2023090601A1 - User terminal and method for providing body shape information for each body part of user

Info

Publication number: WO2023090601A1
Application number: PCT/KR2022/013223
Authority: WO
Inventors: 염세경; 김창균; 김민지
Original assignee: 동국대학교 산학협력단
Priority date: 2021-11-18
Filing date: 2022-09-02
Publication date: 2023-05-25
Also published as: KR102646272B1; KR20230073381A

Abstract

A user terminal according to an embodiment of the present invention may comprise: a camera unit which captures images of a user to acquire a front two-dimensional image and a side two-dimensional image of the user; a control unit which generates a three-dimensional image of each body part of the user by using the front two-dimensional image and the side two-dimensional image; and an interface unit which provides body shape information for each body part of the user on the basis of the three-dimensional image of each body part.

Description

Method for providing body type information for each user terminal and user's body part

The present invention relates to a user terminal and a method for providing body shape information for each body part of a user.

Recently, people have begun to pay much attention to health, and interest in health care and self-care has also increased. Self-care refers to a method of diagnosing and managing one's own health, collecting information on one's own, and receiving professional help when necessary.

Users are using self-care related services through terminals, and as technology using artificial intelligence has recently developed, smart healthcare services that enhance self-care are being provided.

Existing self-care services provide services such as weight control and obesity management for users, but the data provided through existing services is simply numerical data such as weight-to-height ratio such as BMI (Body Mass Index) or weight. only one In this way, there is a limit to evaluating the user's detailed health condition only with simple numerical data such as weight-to-height ratio or body weight. In particular, there is a growing awareness that 'body shape management' is more important than 'weight control' for health, and many studies on body shape management are being conducted, but self-care services so far have been limited in providing appropriate body shape information. exists.

Therefore, it is necessary to provide users with a service that helps them to manage their own body shape more systematically by recognizing their own body shape and managing their own body shape through this. However, directly measuring the user's body shape has a disadvantage in that it takes a lot of time and money.

To this end, a user is photographed using an external camera, and a 3D model is created using the photographed user's body to provide data to the user, thereby providing body shape information that cannot be measured with indicators such as BMI (body mass index). can be measured, through which the user's body shape and obesity can be diagnosed, and more personalized healthcare services can be provided through comparison with standard body models.

On the other hand, for 3D body modeling, the body can be 3D modeled by synthesizing body images taken from various angles using a camera, or 3D modeling can be performed through shooting and preprocessing using a 3D camera, and 3D scanning It is also possible to use the equipment to scan the user's body and model the body. However, this method has a disadvantage in that it is costly and requires space and time costs.

An object of the present invention is to provide body shape information for each body part of a user by utilizing a front two-dimensional image and a side two-dimensional image of the user.

According to an embodiment of the present invention, a user terminal providing body shape information for each body part of a user includes a camera unit that photographs the user and obtains a front two-dimensional image and a side two-dimensional image of the user; a control unit generating a 3D image for each part of the user's body using the front 2D image and the side 2D image; and an interface unit providing body shape information for each body part of the user based on the 3D image for each body part.

The control unit may generate a 3D image for each body part using an image from which a background part is deleted from each of the front 2D image and the side 2D image.

The control unit generates a front 3D image and a side 3D image by performing 3D modeling on each of the front 2D image and the side 2D image, respectively, and the front 3D image and the side 3D image, respectively. is divided by body part of the user, the divided front 3D images and the divided side 3D images are synthesized for each part of the user's body, and the 3D images for each part are synthesized to use the body part of the user. It may be characterized in that the information on each body type is provided through the interface unit.

The control unit includes an artificial intelligence (AI) processor, the AI processor learns a reference area for dividing the body part of the user according to a supervised learning technique, and the control unit includes the reference area provided from the AI processor. It may be characterized in that the user's body part is distinguished based on.

The interface unit obtains body size information of the user, the control unit integrates the synthesized 3D images for each part, corrects the integrated 3D image using the body size information, and It may be characterized in that body type information for each body part of the user is obtained using an image.

The body size information includes information about the user's height or weight, and the control unit adjusts the height, width, or width of the integrated 3D image based on the body size information. can do.

The body shape information for each body part of the user may include information about a volume or information about a circumference of each part of the user's body.

A method for providing body shape information for each body part of a user according to another embodiment of the present invention includes acquiring a front two-dimensional image and a side two-dimensional image of the user by photographing the user; generating a 3D image for each body part of the user using the front 2D image and the side 2D image; and providing body shape information for each body part of the user based on the 3D image for each body part.

The generating of the 3D image for each body part of the user comprises generating a 3D image for each body part using an image from which a background part is deleted from each of the front 2D image and the side 2D image. can do.

In the generating of the 3D image for each part of the user's body, 3D modeling is performed on each of the front 2D image and the side 2D image to generate a front 3D image and a side 3D image; Segmenting each of the front 3D image and the side 3D image for each body part of the user, synthesizing the divided front 3D images and the divided side 3D images for each part of the user's body, and and providing body shape information for each body part of the user through the interface unit using the synthesized 3D images for each part.

The dividing may include learning a reference region for dividing the user's body part according to a supervised learning technique, and classifying the user's body part based on the reference region. there is.

The step of obtaining body size information of the user may further include, and the step of providing the body shape information for each part of the user's body may include integrating the synthesized 3D images for each part, and converting the integrated 3D image into the body part. It may be characterized by including the step of correcting using size information, and the step of acquiring body shape information for each body part of the user using the integrated 3D image.

The body size information includes information on height or weight of the user, and the modifying step is to adjust the height, width or width of the integrated 3D image based on the body size information. can be done with

According to the present invention, since an image from which a background has been deleted is used, it is possible to obtain more accurate body shape information.

In addition, according to the present invention, it is possible to provide a user's body shape information with only a camera device capable of taking a 2D image without a separate expensive scanning device, and thus it is possible to provide a self-care service at low cost.

In addition, according to the present invention, as long as the mobile terminal is equipped, it is possible to check the user's body change regardless of location, and accordingly, the user can receive the body shape management service at any time.

1 is a flowchart illustrating a method for a user terminal to provide body shape information for each body part of a user according to an embodiment of the present invention.

2 is a diagram illustrating a user terminal and external components for providing body shape information for each body part of a user according to an embodiment of the present invention.

3 is a flowchart illustrating a detailed process of obtaining information necessary for a user terminal to generate body shape information.

4 illustrates a process of acquiring a front 2D image and a side 2D image from a user.

5 is a flowchart illustrating a detailed process in which a user terminal obtains a 3D image for each body part using a 2D image.

6 shows a front/side two-dimensional image with the background removed.

7 shows the result of 3D modeling for a front/side 2D image.

8 shows 3D images separated for each body part.

9 is a flowchart illustrating a detailed process of generating body shape information for each body part using front/side 3D images.

10 and 11 illustrate a process of synthesizing 3D images for each part.

12 shows a process of resizing an entire 3D image.

13 illustrates an example of deriving body type information from a resized entire 3D image.

14 shows an example of providing body type information.

All embodiments described below are shown by way of example to help understanding of the present invention, and may be modified differently from the embodiments described herein and implemented in various embodiments. In addition, in describing the present invention, if it is determined that a detailed description of a related known function or known component may unnecessarily obscure the gist of the present invention, the detailed description will be omitted.

The accompanying drawings are not drawn to scale in order to help the understanding of the invention, but the dimensions of some components may be exaggerated, and when reference numerals are given to each component, the same components are shown in different drawings. Even if it is displayed in , it is indicated with the same code as much as possible.

Also, terms such as first, second, A, B, (a), and (b) may be used to describe components of an embodiment of the present invention. These terms are only used to distinguish the component from other components, and the nature, order, or order of the corresponding component is not limited by the term. When an element is described as being 'connected', 'coupled' or 'connected' to another element, the element may be directly connected, coupled or connected to the other element, but not between the element and the other element. It should be understood that another component may be 'connected', 'coupled' or 'connected' between elements.

Therefore, the embodiments described in this specification and the configurations shown in the drawings are only the most preferred embodiments of the present invention and do not represent all of the technical spirit of the present invention, so there may be various modified embodiments of the present invention. .

In addition, the term or word used in the present specification and claims should not be limited to the usual or dictionary meaning, and the inventor can properly define the concept of the term in order to explain his/her invention in the best way. Based on the principle, it should be interpreted as a meaning and concept consistent with the technical idea of the present invention.

Also, singular expressions used in this application include plural expressions unless the context clearly indicates otherwise.

As shown in FIG. 1 , the method of providing body type information for each body part (S100) includes steps S110, S130, and S150, and a detailed description is as follows.

First, the user terminal may capture a front two-dimensional image and a side two-dimensional image of the user (S110).

Here, the 2D image may be captured according to a user or another user's input, may be captured by a camera included in the user terminal, and the captured image may be transmitted to a control unit (or processor) included in the user terminal. there is. A detailed description will be given later.

Subsequently, the user terminal may obtain a 3D image for each part of the user's body using the 2D image obtained by photographing the front/side of the user (S130).

Here, the control unit of the user terminal may perform 3D modeling of the front 2D image and the lateral 2D image using a known algorithm, and based on the modeling result, generate a 3D image in a form classified for each part of the user's body. there is. A detailed description will be given later.

Next, the user terminal may provide the user with body shape information for each body part based on the 3D image generated for each body part (S150).

Here, the user terminal may include a display or a touch screen, and may output body shape information for each body part in the form of an image through the display or touch screen. A detailed description will be given later.

As shown in FIG. 2 , the user terminal 200 may provide body shape information for each body part generated based on an input from the user to the user and an external device. The server is described below as an example of an external device, but is not necessarily limited thereto.

The user terminal may be a fixed terminal implemented as a computer device or a mobile terminal. The user terminal may be, for example, a smart phone, a computer, a laptop computer, a tablet PC, and the like, but is not necessarily limited thereto.

The user terminal may communicate with a server (external device) through a communication network using a wireless or wired communication method.

The server (external device) may be implemented as a computer device that performs calculations based on information received from a user terminal and provides files, contents, services, and the like to the user terminal.

Also, in other embodiments, the user terminal and server may include more components than those of FIG. 2 . However, there is no need to clearly show most of the prior art components. For example, the user terminal may be implemented to include at least some of the above-described interface units or may further include other components such as a transceiver, a Global Positioning System (GPS) module, a camera, various sensors, and a database. .

The user terminal may include an interface unit 210 , a control unit 220 and a communication unit 230 .

The interface unit 210 may include an input/output unit 211 for receiving an input from a user. As an example of the input/output unit, the touch screen 212 may be included, but is not necessarily limited thereto.

The interface unit may include a sensor unit 221 for sensing a user. Specifically, the sensor unit may include a camera 222 for photographing the user.

The camera may acquire a front 2D image by photographing the front of the user or a side 2D image by photographing the side of the user. The camera, sensor unit or interface unit may transmit the acquired front 2D image or side 2D image to the controller. The camera may photograph a user or an external object according to a photographing command transmitted from the controller. The shooting command of the control unit may be generated based on an external input detected by the input/output unit or an external command received from an external device.

The interface unit may include, for example, a device such as a keyboard or a mouse, and the output device may include a device such as a display for displaying a 3D modeled garment.

The control unit may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations. Commands may be provided to the control unit by a memory or a communication unit. For example, the controller may be configured to execute commands received according to program codes stored in a recording device such as a memory.

According to an embodiment of the present invention, the controller may generate body shape information for each body part of the user using the front 2D image and/or the side 2D image transmitted from the interface unit, and the generated body shape information for each body part may be provided through a user or an external device. A detailed description will be given later.

Here, the control unit may include an AI (Artificial Intelligence) processor 221 for separating and classifying the user's body for each part. For example, in order to classify the user's body, the AI processor may learn the user's body part according to a supervised learning method or an unsupervised learning method.

The communication unit may provide a function for communication between the user terminal and an external device (server), and may provide a function for communication with another user terminal or another server (not shown). For example, a request generated by a controller of a user terminal according to a program code stored in a recording device such as a memory may be transmitted to an external device under control of a communication unit. Conversely, control signals, commands, contents, files, etc. provided under the control of the processor of the external device may be received by the user terminal through the communication unit of the user terminal via the communication unit.

Although not shown in FIG. 2, the user terminal may include a memory (not shown). The memory is a computer-readable recording medium, and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. In addition, an operating system and at least one program code (for example, a code for 3D modeling of clothes installed and driven in a user terminal) may be stored in the memory. These software components may be loaded from a computer-readable recording medium separate from a memory using a drive mechanism. The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, software components may be loaded into a memory through a communication unit rather than a computer-readable recording medium. For example, at least one program may be loaded into memory based on a program installed by files provided by developers or a file distribution system (for example, the above-described server) that distributes application installation files.

As shown in FIG. 3, the process of obtaining information necessary for the user terminal to generate body shape information (S110) (same as step S110 in FIG. 1) includes steps S111, S112, and S113. Details are as follows. Same as

First, the user terminal may obtain a front two-dimensional image by photographing the front of the user (S111). For example, the user's front may be defined as a part of the user's body where the face appears.

Next, the user terminal may obtain a side 2D image by photographing the side of the user (S112). For example, the user's side may be defined as a part of the user's body viewed from a direction perpendicular to the user's frontal direction.

Subsequently, the user terminal may obtain information about the user's body size from the user or from an external device (S113). For example, the user terminal may obtain information about the user's body size through a user's input to the user terminal or communication with an external device. For example, information about the user's body size may include information about the user's height or weight.

After performing steps S111, S112, and S113, the user terminal may perform steps S130 and S150, which will be described in detail later. In the following, steps S111, S112 and S113 will be described in detail with reference to FIG. 4 .

As shown in FIG. 4(A), the user terminal may obtain a front 2D image by photographing the front of the user. The frontal 2D image may include both the user's frontal area and the frontal background area.

As shown in FIG. 4(B) , the user terminal may obtain a side 2D image by photographing the side of the user. The side 2D image may include both a side area of the user and a background area in the side direction.

As shown in FIG. 5, the process of acquiring a 3D image for each body part (S130) (same as step S130 in FIG. 1) includes steps S131, S132, S133, S134, S135 and S136, and detailed descriptions are Same as below.

After performing step S110, the user terminal sequentially performs steps S131, S133, and S135, which are processing steps for the front two-dimensional image, and steps S132, S134, and S136, which are processing steps for the side two-dimensional image, sequentially. The processing of the front 2D image and the processing of the lateral 2D image may be performed simultaneously.

After performing step S110, the user terminal may delete the frontal direction background area from the frontal two-dimensional image (FIG. 4(A)), leaving only the user's frontal area. Also, after performing step S110, the user terminal may delete the background area in the side direction from the side 2D image (FIG. 4(B)), leaving only the user's side area. By removing the background except for the human form from the front 2D image and the side 2D image, noise in 3D modeling to be performed later can be minimized in advance, thereby creating a 3D body model with high accuracy. there is.

Then, after performing step S131, the user terminal may perform 3D modeling on the front 2D image from which the background is removed (S133). By performing step S133, the user terminal can generate a front 3D image. Also, after performing step S132, the user terminal may perform 3D modeling on the side 2D image from which the background is removed (134). By performing step S134, the user terminal can generate a side 3D image.

The process of 3D modeling the front 2D image and the side 2D image into the front 3D image and the side 3D image, respectively, may be performed by modifying a known 3D generating deep learning method. As an example of a known 3D generation deep learning methodology, there is a Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization (PIFuHD) algorithm, but this has a disadvantage in that it does not reflect depth information. In order to compensate for this disadvantage, in the present invention, the user terminal performs 3D modeling using both the front 2D image and the side 2D image. More specifically, the frontal 3D image created using the frontal 2D image has information on the body shape and depth of the front of the user, and the side 3D image created using the side 2D image has information on the user's frontal body shape and depth. It has body shape and depth information. That is, the front 3D image and the side 3D image according to an embodiment of the present invention are composed of mesh-type data sets.

Subsequently, after performing step S133, the user terminal may divide the front 3D image for each body part (S135). For example, the control unit of the user terminal may classify the user's body part by part based on a criterion learned through an AI processor included in the control unit. The controller may divide the frontal 3D image for each part of the user's body. Also, after performing step S134, the user terminal may divide the side 3D image for each body part (S136). A method of segmenting the side 3D image for each body part is the same as the method of segmenting the frontal 3D image. As described above, by separating the user's body for each body part, accuracy can be increased more than when synthesizing the front 3D image and the side 3D image in step S150 later.

After performing steps S135 and S136, the user terminal performs step S150, which will be described in detail later.

6 shows a front/side two-dimensional image with the background removed.

As shown in FIG. 6(A), the user terminal may delete the frontal direction background area from the frontal 2D image, leaving only the frontal area 610 of the user's body.

As shown in FIG. 6B , the user terminal may delete the background area in the side direction from the side 2D image, leaving only the side area 620 of the user's body.

As described above, by deleting the background area from the front/side 2D image, accuracy of a 3D model to be performed later can be further increased.

7 shows the result of 3D modeling for a front/side 2D image.

As shown in FIG. 7(A), the user terminal may obtain a front 3D image 710 by performing 3D modeling on the front 2D image from which the background is removed. Here, the frontal 3D image includes information about the frontal body shape of the user's body and information about the depth in the frontal direction.

As shown in FIG. 7B , the user terminal may obtain a side 3D image 720 by performing 3D modeling on the side 2D image from which the background is removed. Here, the side 3D image includes information about the body shape of the side of the user's body and information about the depth in the side direction.

8 shows 3D images separated for each body part.

As shown in FIG. 8(A), the user terminal may divide the generated frontal 3D image 810 by body part based on the criteria learned by the AI processor. For example, the user terminal converts the front 3D image into a right arm front 3D image 811, a left arm front 3D image 812, a torso front 3D image 813, and a right leg front 3D image 814. , The front 3D image 815 of the left leg can be divided into parts.

As shown in FIG. 8(B) , the user terminal may divide the generated side 3D image 820 by body part based on the criteria learned by the AI processor. For example, the user terminal displays a side 3D image as a right arm side 3D image 821, a left arm side 3D image 822, a torso side 3D image 823, and a right leg side 3D image 824. , The left leg side 3D image 825 can be divided into parts.

As shown in FIG. 9, the detailed process of generating body shape information (S150) includes steps S151, S152, S153, and S154, and detailed descriptions are as follows.

First, after performing steps S110 and S130, the user terminal may synthesize a front 3D image for each body part and a side 3D image for each body part (S151). Specifically, the user terminal synthesizes the right arm front 3D image 811 described with reference to FIG. 8 with the right arm side 3D image 821, and the left arm front 3D image 812 is left arm side 3 It is synthesized with the dimensional image 822, the torso front 3D image 813 is combined with the torso side 3D image 823, the right leg front 3D image 814 is combined with the right leg lateral 3D image 824 In addition, the front 3D image 815 of the left leg may be synthesized with the 3D image 825 of the side of the left leg.

Next, the user terminal may integrate the 3D images synthesized for each body part into an entire 3D image of the user's body (S152). That is, the user terminal may generate an entire 3D image by combining all the 3D images for each part of the user's body synthesized in step S151.

Subsequently, the user terminal may resize the entire 3D image using the information about the user's body size obtained in step S113 of FIG. 3 (S153). For example, the user terminal may enlarge or reduce the height or width of the entire 3D image based on information about the user's height and/or the user's weight.

Next, the user terminal may obtain body shape information for each body part of the user by using the resized entire 3D image (S154). For example, the user terminal may extract body type information such as length, circumference, or volume information for each body part within the entire resized 3D image.

10 and 11 illustrate a process of synthesizing 3D images for each part.

As shown in FIG. 10, the user terminal may generate a synthesized 3D image 1003 by synthesizing a torso front 3D image 1001 and a torso side 3D image 1002, and as shown in FIG. 11, the rest of the body The entire 3D image 1101 may be generated by combining parts in the same manner.

12 shows a process of resizing an entire 3D image.

As shown in FIG. 12 , the user terminal enlarges/reduces the length of the

entire 3D images

1201 and 1202 by using the user's body size information (eg, weight or height), or the entire 3D image 1201 , 1202) can be enlarged/reduced.

As shown in FIG. 13, the user terminal analyzes the arm of the entire resized 3D image 1300, and obtains information on the length of the arm 1311, information on the circumference of the arm 1312, and torso. Information on the length of the part (1331), information on the circumference of the body part (1332), information on the length of the leg part (1321), and information on the circumference of the leg part (1322) can be derived. Also, the user terminal may provide the derived body shape information to the user or an external device.

An example of providing body shape information to a user or an external device is exemplified through FIG. 14 .

14 shows an example of providing body type information.

As shown in FIG. 14 , the user terminal can acquire body shape information of user 1 and body shape information of user 2 through the method described above with reference to FIGS. 1 to 13 .

Next, the user terminal may place the avatar 1 1410 in a 'virtual space' or a 'metaverse' based on user 1's body shape information. Similarly, the user terminal may place the avatar 2 1420 in a 'virtual space' or a 'metaverse' based on user 2 body shape information.

Within the virtual space or metaverse, Avatar 1 and Avatar 2 may share body shape information with each other. That is, here, avatar 1 can be a virtual 'doctor' role, and the 'doctor' role can share body shape information of avatar 2 and perform telemedicine on avatar 2.

Also, for example, Avatar 1 may be operated in conjunction with User 1's movement and operated in the same way as User 1's movement, and Avatar 2 may also be operated similarly.

Although the embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and may be variously modified and implemented without departing from the technical spirit of the present invention.

Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

[Description of code]

200: user terminal

210: interface unit

220: control unit

230: communication department

Claims

In a user terminal providing body shape information for each body part of a user,

a camera unit for photographing the user and acquiring a front two-dimensional image and a side two-dimensional image of the user;

a control unit generating a 3D image for each part of the user's body using the front 2D image and the side 2D image; and

An interface unit providing body shape information for each body part of the user based on the 3D image for each body part,

user terminal.
According to claim 1,

The control unit,

Characterized in that a three-dimensional image for each body part is generated using an image from which a background part is deleted from each of the front two-dimensional image and the side two-dimensional image,

user terminal.
According to claim 2,

The control unit,

3D modeling is performed on each of the front 2D image and the side 2D image to generate a front 3D image and a side 3D image;

Dividing each of the front 3D image and the side 3D image for each part of the user's body;

synthesizing the divided frontal 3D images and the divided side 3D images for each part of the user's body;

Characterized in that the body shape information for each body part of the user is provided through the interface unit using the synthesized 3D images for each part.

user terminal.
According to claim 3,

The control unit includes an AI (Artificial Intelligence) processor,

The AI processor,

Learning a reference region for dividing the user's body part according to a supervised learning technique;

The control unit,

Characterized in that the user's body part is distinguished based on the reference region provided from the AI processor.

user terminal.
According to claim 3,

The interface unit acquires body size information of the user;

The control unit,

Integrating the 3D images for each of the synthesized parts,

Correcting the integrated 3D image using the body size information,

Characterized in that body shape information for each body part of the user is obtained using the integrated 3D image,

user terminal.
According to claim 5,

The body size information includes information on height or weight of the user,

The control unit,

Characterized in that the height, width or width of the integrated 3D image is adjusted based on the body size information,

user terminal.
According to claim 6,

Characterized in that the body shape information for each part of the user's body includes information about the volume or information about the length of the circumference of each part of the user's body.

user terminal.
A method for a user terminal to provide body shape information for each body part of a user, the method comprising:

acquiring a front two-dimensional image and a side two-dimensional image of the user by photographing the user;

generating a 3D image for each body part of the user using the front 2D image and the side 2D image; and

Providing body shape information for each body part of the user based on the 3D image for each body part,

method.
According to claim 8,

The step of generating a 3D image for each part of the user's body,

Characterized in that a three-dimensional image for each body part is generated using an image from which a background part is deleted from each of the front two-dimensional image and the side two-dimensional image,

method.
According to claim 9,

The step of generating a three-dimensional image for each part of the user's body,

Generating a front 3-dimensional image and a side 3-dimensional image by performing 3-dimensional modeling on each of the front 2-dimensional image and the side 2-dimensional image;

Segmenting each of the front 3-dimensional image and the side 3-dimensional image for each part of the user's body;

Synthesizing the divided front 3D images and the divided side 3D images for each part of the user's body, and

and providing body shape information for each body part of the user through the interface unit using the synthesized 3D images for each part.

method.
According to claim 10,

The dividing step is

Learning a reference region for dividing the user's body part according to a supervised learning technique; and

Characterized in that it comprises the step of classifying the user's body part based on the reference area,

method.
According to claim 10,

Further comprising obtaining body size information of the user,

The step of providing body shape information for each body part of the user,

Integrating the three-dimensional images for each part of the synthesis;

modifying the integrated 3D image using the body size information; and

Characterized in that it comprises the step of obtaining body shape information for each body part of the user using the integrated 3D image,

method.
According to claim 12,

The body size information includes information on height or weight of the user,

The correction step is

Characterized in that adjusting the height, width or width of the integrated 3D image based on the body size information,

method.
According to claim 13,

Characterized in that the body shape information for each part of the user's body includes information about the volume or information about the length of the circumference of each part of the user's body.

method.