KR102477338B1 - Method, apparatus and program for providing facial mood diagnosis platform using image - Google Patents

Abstract

The present invention relates to a method, a device, and a program for providing a facial mood diagnosis platform using images. The present invention analyzes facial features using images taken of a user's face, diagnoses adjectives that correspond to the user's facial mood, and provides the same to the user. The method for providing a facial mood diagnosis platform using images according to an embodiment of the present invention comprises the steps of: obtaining an image of a face from a user; setting a reference point that defines a face within the obtained image; and determining facial features using set reference points, and determining an adjective corresponding to the facial mood of the user using the results of determining the facial features.

Description

Method, apparatus and program for providing facial mood diagnosis platform using image {METHOD, APPARATUS AND PROGRAM FOR PROVIDING FACIAL MOOD DIAGNOSIS PLATFORM USING IMAGE}

The present invention relates to a method, apparatus, and program for providing a platform for diagnosing facial mood using images. The present invention relates to a method, apparatus, and program for providing a facial mood diagnosis platform using an image provided to a user.

BACKGROUND ART [0002] Recently, as interest in beauty has rapidly increased in modern society, a beauty industry is developing. As the beauty industry develops, users tend to show increased interest in makeup, clothing, hair, and the like.

However, since skin color, face shape, features, etc., of each user are diverse, makeup, clothes, hair, etc. suitable for each individual may be different. Therefore, users want to find makeup, clothes, and hair designs that suit them, but in order to find a design that suits them, they have to go through a lot of trial and error, which takes a lot of time and money.

In this way, in order to find a design that suits oneself, it is important to objectify the image from the user's individual face, but it is difficult to objectify the image because subjective opinions are easily reflected according to the user's gaze.

The problem to be solved by the present invention is to analyze facial characteristics using an image of a user's face, diagnose adjectives corresponding to the user's facial mood, and provide a facial mood diagnosis platform using images provided to the user; To provide devices and programs.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

A method for providing a facial mood diagnosis platform using an image according to an embodiment of the present invention for solving the above problems includes acquiring an image of a face taken from a user, and setting a reference point defining a face in the obtained image. The method may include determining facial features using set reference points, and determining an adjective corresponding to the facial mood of the user using a result of determining the facial features.

In addition, the step of determining the feature of the face may include obtaining a reference point group designating each feature of the face, determining a positional relationship between the reference points corresponding to the reference point group, and determining the facial features based on the determined result. It may include defining a shape.

In addition, the step of determining the adjective corresponding to the facial mood of the user may include setting a plurality of categories according to the facial mood, matching and storing adjectives corresponding to each of the plurality of categories, and storing the adjective corresponding to the plurality of categories. The step of selecting a category corresponding to the feature of the face, and based on the adjectives included in the selected category, a representative adjective that best matches the facial mood of the user, a reinforcing adjective that reinforces the facial mood of the user, and the The method may include determining at least one adjective among complementary adjectives that complement the user's face mood.

The method may also include setting a coordinate plane in which regions are set according to characteristics of the plurality of categories, designating coordinate values of each of the adjectives, and setting a plurality of category regions on the coordinate plane. .

In addition, calculating x and y values for each of the defined features, specifying coordinates corresponding to the calculated x and y values on the coordinate plane, and the closest distance to the specified coordinate values A step of selecting a category to be located may be included.

In addition, the step of extracting adjectives corresponding to the selected category, the step of extracting adjectives whose x value or y value satisfies a specific criterion according to the characteristics of the category among the extracted adjectives, and the extracted adjectives to the user A step of providing an adjective corresponding to the facial mood may be included.

In addition, the step of arranging the order of the extracted adjectives in the order of having the coordinate value of the position closest to the specified coordinate value among the plurality of adjectives extracted for each of the defined features, and based on the order of the adjectives The method may include selecting a representative adjective and providing the user with at least one of the adjectives up to a specific rank among the adjectives in the order and the representative adjective.

In addition, based on the x-value and y-value of the adjective corresponding to the facial mood of the user, calculating an x-value and a y-value that are symmetrical about the x-axis, y-axis and the origin, and the calculated x-value and y-value The method may include selecting a category located closest to a coordinate value corresponding to the value, and providing the category or an adjective corresponding to the category as a supplementary adjective that complements the user's facial atmosphere.

The method may also include acquiring clothing information from a shopping mall, extracting clothing atmosphere based on the clothing information, and providing clothing with an atmosphere suitable for the user to the user.

An apparatus for providing a platform for diagnosing facial mood using images according to an embodiment of the present invention for solving the above problems includes a memory for storing one or more instructions, and a processor for executing the one or more instructions stored in the memory, The processor may perform the method of providing a platform for diagnosing facial mood using an image by executing the one or more instructions.

A program for providing a facial mood diagnosis platform using an image according to an embodiment of the present invention for solving the above problems is combined with a computer, which is hardware, and is readable by a computer to perform a method for providing a facial mood diagnosis platform using an image. It can be stored on a recording medium.

Other specific details of the invention are included in the detailed description and drawings.

According to the present invention, facial features may be analyzed using an image of a user's face, and adjectives corresponding to the mood of the user's face may be diagnosed and provided to the user.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram illustrating a system for providing a platform for diagnosing facial mood using images according to an embodiment of the present invention.
2 is a hardware configuration diagram of a platform providing device according to an embodiment of the present invention.
3 is a diagram illustrating a method for providing a facial mood diagnosis platform using an image according to an embodiment of the present invention.
4 is a diagram illustrating an example of a coordinate plane in which areas are set according to characteristics of a plurality of categories according to an embodiment of the present invention.
5 is a diagram showing an example of specifying coordinate values for features according to an embodiment of the present invention.
6 is a diagram illustrating an example of selecting a complementary adjective according to an embodiment of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to an embodiment. For example, a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least a part of each step may be performed in different devices according to embodiments.

1 is a diagram illustrating a system for providing a platform for diagnosing facial mood using images according to an embodiment of the present invention.

Referring to FIG. 1 , a system for providing a platform for diagnosing facial mood using images according to an embodiment of the present invention may include a platform providing device 100 , a user terminal 200 and an external server 300 .

Here, the system for providing a facial mood diagnosis platform using the image shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added, changed, or deleted as necessary. can

A system for providing a platform for diagnosing facial mood using images according to an embodiment of the present invention may analyze facial characteristics using an image of a user's face, diagnose adjectives corresponding to the user's facial mood, and provide the diagnosed adjectives to the user. have. The user may be provided with a platform for diagnosing facial mood using images through the user terminal 200 , and the user may provide the platform with an image of a face captured through the user terminal 200 .

The platform providing device 100 acquires an image of a face taken from the user, sets reference points defining the face in the acquired image, determines facial characteristics using the set reference points, and determines the facial characteristics as a result of determining the result. Adjectives corresponding to the facial mood of the user may be determined using .

The user terminal 200 may be connected to the platform providing device 100 through a network and may receive various services and platforms from the platform providing device 100 .

The user terminal 200 can receive various services provided by the platform providing device 100 through applications by downloading, installing, and executing various services provided by the platform providing device 100 and applications related to the platform. To this end, the user terminal 200 may be equipped with an operating system capable of driving applications like a smart phone. However, the user terminal 200 is not limited thereto, and other general-purpose devices capable of driving applications may be applied.

In various embodiments, the user terminal 200 may provide a service based on the web as well as an application, and a method of providing the service by the user terminal 200 is not limited to a specific format.

The external server 300 may be connected to the platform providing device 100 through a network, and the platform providing device 100 may store and manage various information for performing a method of providing a facial mood diagnosis platform using an image.

In addition, the external server 300 may receive and store various types of information and data generated as the platform providing device 100 performs a method for providing a facial mood diagnosis platform using an image. For example, the external server 300 may be a storage server provided separately outside the platform providing device 100 . Referring to FIG. 2 , the hardware configuration of the platform providing apparatus 100 will be described.

2 is a hardware configuration diagram of a platform providing device according to an embodiment of the present invention.

Referring to FIG. 2 , a platform providing device 100 (hereinafter referred to as a computing device) according to an embodiment of the present invention loads one or more processors 110 and a computer program 151 executed by the processor 110. ) may include a memory 120, a bus 130, a communication interface 140, and a storage 150 for storing the computer program 151. Here, in FIG. 2, only components related to the embodiment of the present invention are shown. Therefore, those skilled in the art to which the present invention pertains can know that other general-purpose components may be further included in addition to the components shown in FIG. 2 .

The processor 110 controls the overall operation of each component of the computing device 100 . The processor 110 includes a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present invention. It can be.

Also, the processor 110 may perform an operation for at least one application or program for executing a method according to embodiments of the present invention, and the computing device 100 may include one or more processors.

In various embodiments, the processor 110 may temporarily and/or permanently store signals (or data) processed in the processor 110 (RAM: Random Access Memory, not shown) and ROM (ROM: Read -Only Memory, not shown) may be further included. In addition, the processor 110 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 may perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The bus 130 provides a communication function between components of the computing device 100 . The bus 130 may be implemented in various types of buses such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the computing device 100 . Also, the communication interface 140 may support various communication methods other than internet communication. To this end, the communication interface 140 may include a communication module well known in the art. In some embodiments, communication interface 140 may be omitted.

The storage 150 may non-temporarily store the computer program 151 . When the method for providing a facial mood diagnosis platform using an image is performed through the computing device 100, the storage 150 may store various types of information required to provide a method for providing a facial mood diagnosis platform using an image.

The storage 150 may be a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or the like, a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.

Computer program 151 may include one or more instructions that when loaded into memory 120 cause processor 110 to perform methods/operations in accordance with various embodiments of the invention. That is, the processor 110 may perform the method/operation according to various embodiments of the present disclosure by executing the one or more instructions.

In an embodiment, the computer program 151 may perform the steps of obtaining an image of a face taken from a user, setting reference points defining a face in the obtained image, and determining characteristics of the face using the set reference points. , may include one or more instructions for performing a method for providing a platform for diagnosing a facial mood using an image, including determining an adjective corresponding to a facial mood of a user using a result of determining a facial feature.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), can be implemented in a programming or scripting language such as assembler (assembler). Functional aspects may be implemented in an algorithm running on one or more processors. Hereinafter, with reference to FIG. 3 , a method for providing a facial mood diagnosis platform using an image provided by the computing device 100 will be described.

3 is a diagram illustrating a method for providing a facial mood diagnosis platform using an image according to an embodiment of the present invention.

Referring to FIG. 3 , the computing device 100 may acquire an image of a user's face (S100). The computing device 100 may provide instructions for performing a facial mood diagnosis system using images through the user terminal 200, and the user may receive an image of a face captured by following the instructions provided through the user terminal 200. may be provided to the computing device 100.

The computing device 100 may provide an instruction for the user to photograph a face through the facial mood diagnosis platform, and the user may photograph his/her own face according to the instruction. An image captured through the user terminal 200 may be provided to the computing device 100 through a facial mood diagnosis platform.

Meanwhile, the computing device 100 may provide an instruction to upload the photographed image to the facial mood diagnosis platform, and the user may upload the photographed image of his/her own face according to the instruction. An image uploaded through the user terminal 200 may be provided to the computing device 100 through the facial mood diagnosis platform.

The computing device 100 may check the color and composition of the acquired image, request recapture of the image, or request upload of another image. For example, if the image is too bright, the user's face may not be properly recognized. Therefore, a recapture of the image may be requested or another image may be uploaded to obtain an image capable of recognizing the user's face.

In addition, if only a part of the user's face is captured, the user is not facing the front, or the face is captured too far or too close, the computing device 100 requests the image to be recaptured or another image to be uploaded so that the user's face is captured. A recognizable image of can be obtained.

The computing device 100 may set a reference point for defining a face in the acquired image (S200). Reference points for defining the face may include all points that can define the face, such as the tail of the eyes, the pupil, the tip of the nose, the bridge of the nose, the head of the eyebrow, the tail of the eyebrow, the chin line, the forehead line, the lips, the authentication point, and the middle of the forehead. The computing device 100 may classify facial features based on a reference point. For example, the computing device 100 may determine the position and shape of the eyes based on reference points set at the outer corners of the eyes, pupils, and brows, and through this, it may be possible to distinguish features.

For example, the computing device 100 may set a reference point for defining a face in an image. Reference points defining the face may include the tail of the eyes, the pupil, the tip of the nose, the nostrils, the head of the eyebrows, the tails of the eyebrows, the chin line, the forehead line, the lips, the authentication point, and the eyebrows.

The computing device 100 may determine facial features using set reference points (S300). The computing device 100 may obtain a reference point group designating each facial feature. For example, the computing device 100 may create one reference point group by extracting reference points defining the eyes. That is, the computing device 100 may create one group including reference points designating the eyes, such as the tail of the eyes, the pupils, the lids, and the forehead. The computing device 100 may create each reference point group including reference points corresponding to positions of the face, eyes, nose, and mouth.

For example, the computing device 100 may obtain a reference point group designating each facial feature. For example, the computing device 100 may create one reference point group (eg, G1) defining the eyes from the reference points set at the corner of the eyes, the pupil, the lids, and the crown of the eyes. In addition, the computing device 100 may generate one reference point group (eg, G2) defining the eyebrows by reference points set at the eyebrow head, the eyebrow tail, and the center of the eyebrow. In addition, the computing device 100 may create one reference point group (eg, G3) defining the mouth with reference points set at both ends of the lips, the corners of the lips, and the center of the lips. In the above-described embodiment, only the creation of reference point groups for the eyes, eyebrows, and mouth is disclosed, but is not limited thereto, and reference point groups can be created for all features of the face, such as the forehead, face shape, and nose. have.

Referring back to FIG. 3 , the computing device 100 may determine distances between reference points corresponding to a reference point group and locations of the reference points. For example, the distance between the reference point set at the outer corner of the eye and the reference point set at the front of the eye among the reference points included in the group of reference points defining the eyes, the distance between the reference points set above and below the eye based on the pupil, etc. The shape of the eye can be determined, and the position of the eye can be determined by determining at which position on the face the reference point group defining the eye is placed. The computing device 100 may define the shape of the features based on the determined result, and may be able to define the shape and position of all components that are characteristics of the face, such as the eyes, nose, face shape, and forehead line. .

The computing device 100 may determine an adjective corresponding to the facial mood of the user by using the result of determining the facial characteristics (S400). Specifically, the computing device 100 may set a plurality of categories according to images that can be distinguished according to facial moods, and the plurality of categories may include a baby face image, a sophisticated image, a friendly image, and an activity image. It is not limited to this.

The computing device 100 may match and store adjectives corresponding to each of a plurality of categories. That is, the computing device 100 may match and store 'elegant', 'classy', and 'urban' as adjectives related to the sophisticated image, and 'cute' and 'girlish' as adjectives related to the childish image. Matching can be saved. Adjectives corresponding to each category may be set differently for each category, and as described above, it may be possible to set them overlappingly.

The computing device 100 stores categories and adjectives for each category, determines a corresponding category according to facial features determined through images, and diagnoses the user's facial mood through the adjectives for each category.

That is, the computing device 100 may select a category corresponding to facial features from among a plurality of categories. For example, as a result of analyzing the characteristics of the face, when the face shape is round, a category for a baby face image may be selected. On the other hand, as a result of analyzing the facial features, if the eyebrows are drooping, a category for the friendly image may be selected. The computing device 100 may store categories for each facial feature, and extract and select a category corresponding to the feature. For example, the computing device 100 may store drooping eyes as a facial feature corresponding to a category for a friendly image, and when the facial feature is determined to be eyes with drooping eyelids through an image, the computing device 100 selects a category. You can select a friendly image.

Based on the adjectives included in the selected category, the computing device 100 selects at least one of a representative adjective that best matches the user's facial mood, a reinforcing adjective that enhances the user's facial mood, and a supplementary adjective that complements the user's facial mood. adjectives can be determined. The computing device 100 may provide the determined adjective to the user.

Specifically, the computing device 100 may set a coordinate plane in which an area is set according to characteristics of a plurality of categories. Here, in the coordinate plane, the first category is set in a first region with a large y value, the second category is set in a second region with small x and y values, and the third category is set in a third region with a large x value. and a fourth category may be set in a fourth region having a large x value and a small y value.

However, the area set on the coordinate plane for each category may not be limited to this, and according to an embodiment of the present invention, the area according to the characteristics of a plurality of categories may be set in the first quadrant, but is not limited thereto. That is, the regions according to the characteristics of the plurality of categories may be set in the second quadrant, the third quadrant, and the fourth quadrant, respectively, and the sizes and positions of the regions according to the plurality of categories set in each quadrant may be different. have.

4 is a diagram illustrating an example of a coordinate plane in which areas are set according to characteristics of a plurality of categories according to an embodiment of the present invention.

Referring to FIG. 4 , the computing device 100 sets a first category in a first region having a large y value, sets a second category in a second region having a small x value and a small y value, and sets a second category having a large x value. A third category may be set in region 3, and a fourth category may be set in a fourth region having a large x value and a small y value. However, the area designated according to each category is not limited thereto, and the size and location of each area may not be limited thereto.

In addition, each range of the first area, the second area, the third area, and the fourth area may be designated and set. In this case, the designated value may not be preset. For example, the first area is designated as an area where the y value is 8 or more, the second area is designated as an area where the x value is less than 5 and the y value is less than 5, and the third area is designated as an area where the x value is 10 or more. designated, and the fourth region may be designated as a region in which an x value is 7 or more and a y value is less than 3. However, the range designated for each area is not limited thereto.

Referring back to FIG. 3 , the computing device 100 may designate coordinate values of each adjective. Coordinate values of each adjective may be designated based on a region for each characteristic of the plurality of categories. For example, in the case of the adjective 'cute', it may be an adjective included in both a baby image and a friendly image. On the other hand, if the category for baby-faced images is set in the fourth area and the category for friendly images is set in the third area, coordinate values with a large x value and a small y value may be designated for the adjective 'cute'.

The computing device 100 may calculate an x value and a y value for each of the defined features. The computing device 100 may calculate various indices representing the shape and positional relationship of each of the features constituting the face using the reference point, and may obtain an x value and a y value for the index. The computing device 100 may calculate an x value and a y value for each feature through a preset reference point among reference points included in each reference point group. For example, in the case of the eyelid drooping index, x values and y values for the drooping eyes index may be calculated using a reference point set at the eyelid and a reference point set at the outer corner of the eye.

The computing device 100 may specify coordinate values corresponding to the calculated x and y values to the coordinate plane. That is, the computing device 100 may specify coordinate values for each feature on a coordinate plane in which areas are set according to characteristics of a plurality of categories. The computing device 100 may select a category located closest to the specified coordinate value. The computing device 100 may provide the selected category as a category corresponding to the facial mood of the user. Here, a plurality of categories may be selected as categories are selected for each feature shape, and at this time, the computing device 100 may select the category selected in the largest number as the representative category. Also, the computing device 100 may set a weight according to the shape of the features, and select a category having the largest value according to the weight as the representative category.

5 is a diagram showing an example of specifying coordinate values for features according to an embodiment of the present invention.

Referring to FIG. 5 , the computing device 100 may calculate various indices representing the shape and positional relationship of each feature constituting the face using a reference point, and obtain an x value and a y value for the index. The computing device 100 may specify coordinate values (v) corresponding to the calculated x and y values to the coordinate plane. That is, the computing device 100 may specify a coordinate value v for each feature on a coordinate plane in which regions are set according to characteristics of a plurality of categories. The computing device 100 may select a category located closest to the specified coordinate value (v). That is, the computing device 100 may select the first category assigned to the first area closest to the coordinate values v1, v2, v3, and v4, and select the first category assigned to the second area closest to the coordinate value v5. The second category may be selected, and the third category assigned to the third area closest to the coordinate value v6 may be selected.

The computing device 100 may select the first category selected as the largest number as the representative category. Also, the computing device 100 may set a weight according to the shape of the features, and select a category having the largest value according to the weight as the representative category.

Referring back to FIG. 3 , the computing device 100 may extract adjectives corresponding to the selected category. The computing device 100 may extract adjectives whose x-values or y-values satisfy a specific criterion according to the characteristics of the category from among the extracted adjectives.

For example, when the selected category is the first category, the computing device 100 may extract adjectives having a y-value greater than a specified coordinate value from among adjectives included in the first category. Also, when the selected category is the second category, the computing device 100 may extract adjectives having a y-value smaller than the specified coordinate value from among adjectives included in the second category. Also, when the selected category is the third category, the computing device 100 may extract adjectives having an x-value greater than the specified coordinate value from among adjectives included in the third category. Also, when the selected category is the fourth category, the computing device 100 may extract adjectives having an x-value smaller than the specified coordinate value from among adjectives included in the fourth category.

The computing device 100 may provide the extracted adjective as an adjective corresponding to the user's face mood.

Also, the computing device 100 may rank the extracted adjectives in the order of having the coordinate value of the position closest to the specified coordinate value among the plurality of adjectives extracted for each defined feature shape. Here, the coordinate value of the position closest to the specified coordinate value can be calculated through a formula for obtaining the distance between coordinates, and the extracted adjectives can be ranked in the order of the adjective having the smallest coordinate value as a result of the calculation. have.

The computing device 100 may rank the adjectives for each category selected according to facial features, and provide the adjectives up to a specific order for each category to the user. For example, if the category selected according to facial characteristics is a baby face image and an activity image, the computing device 100 may rank the order of adjectives included in the baby face image and the order of the adjectives included in the activity image. . Thereafter, the computing device 100 may provide the user with adjectives corresponding to the third rank among the adjectives included in the baby boy image, and provide the adjectives corresponding to the third rank among the adjectives included in the activity image to the user. .

Also, the computing device 100 may select representative adjectives based on the order of adjectives in each category. The representative adjective may be selected based on the highest ranked adjective in each category, and the adjective in the representative category or the adjective in the category having the highest value according to weight may be selected as the representative adjective.

In addition, the computing device 100 may calculate x-values and y-values that are symmetrical about the x-axis, the y-axis, and the origin, based on the x-value and y-value of the adjective corresponding to the facial mood of the user. The computing device 100 may select a category located closest to the coordinate values corresponding to the calculated x and y values, and use the selected category or an adjective corresponding to the selected category to complement the user's facial atmosphere. It can be provided to the user as a complementary adjective.

6 is a diagram illustrating an example of selecting a complementary adjective according to an embodiment of the present invention.

Referring to FIG. 6 , the computing device 100 may calculate x values and y values for each facial feature of the user, and specify coordinates corresponding to the calculated x and y values on the coordinate plane. The computing device 100 may select a category set in an area located closest to the coordinate value v1 specified on the coordinate plane as a representative category, and determine adjectives included in the representative category as adjectives corresponding to facial moods. have.

The computing device 100 may calculate a coordinate value v2 that is symmetrical to the specified coordinate value v1. The computing device 100 may calculate a coordinate value v2 that is symmetrical with respect to the x-axis, the y-axis, and the origin. For example, if the x value of the specified coordinate value (v1) is 10 and the y value is 12, the coordinate value (v2) with the x value 10 and the y value -12 is calculated symmetrically about the x axis can do. In addition, when the x value of the specified coordinate value v1 is 10 and the y value is 12, the coordinate value v2 having an x value of -10 and a y value of 12 can be calculated symmetrically about the y axis , and a coordinate value (v2) having an x value of -10 and a y value of -12 can be calculated symmetrically about the origin.

Sizes and locations of regions for a plurality of categories set in each quadrant on the xy plane may all be different, and categories at locations closest to the symmetrical coordinate values v2 may also all be different. That is, when the coordinate value v1 specified in the first quadrant is symmetrical about the x-axis, the symmetrical coordinate value v2 is specified in the fourth quadrant, and the coordinate value v1 specified in the first quadrant is symmetrical about the y-axis. The coordinate value (v2) that is symmetrical when symmetrical about the reference is specified in the second quadrant, and the coordinate value (v2) that is symmetrical when the coordinate value (v1) specified in the first quadrant is symmetrical about the origin is the symmetrical coordinate value (v2) in the third quadrant can be specified in In this case, the categories closest to the coordinate values specified in the first quadrant, the second quadrant, the third quadrant, and the fourth quadrant may all be different. Meanwhile, it is possible that all the same categories are selected, and some of the same categories and some of the different categories may be selected.

The computing device 100 may select a category selected from the symmetrical coordinate values as a supplementary category, determine an adjective corresponding to the supplementary category as a supplemental adjective capable of complementing a facial atmosphere, and provide the selected adjective to the user.

According to an embodiment of the present invention, the computing device 100 may obtain clothing information from a shopping mall. Clothing information may acquire all information related to clothing, such as the shape, color, size, vendor, type, and fabric of clothing, but is not limited thereto.

The computing device 100 may determine representative mood information of clothing based on the acquired clothing information. For example, the computing device 100 may determine the atmosphere of the clothing based on various attribute information such as the style, type, and color of the corresponding clothing.

The computing device 100 may provide clothing information to the user according to information matching the determined atmosphere of the clothing and the user's atmosphere. For example, the computing device 100 may process 3D distance information between the user's mood and the clothes' mood and provide clothing information in an order suitable to the user.

Alternatively, the computing device 100 may recommend clothing having a different mood that can complement the user's mood. For example, the user's mood may be strengthened by recommending clothes that match the user's mood, but the user's mood may be changed differently by recommending clothes with a different atmosphere from the user's mood.

As described above, according to an embodiment of the present invention, facial features are analyzed using a photographed image of the user's face, adjectives corresponding to the user's facial mood are diagnosed, and facial mood diagnosis using the provided image is provided to the user. A platform providing method, device, and program can be realized.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100: computing device
200: user terminal
300: external server

Claims (11)

In a method performed by a computing device,
Obtaining a photographed image of a face from a user;
setting a plurality of reference points defining a face in the obtained image;
calculating a plurality of indices representing different facial features by using the positional relationship of the plurality of set reference points, and obtaining coordinate values corresponding to each of the plurality of indices;
setting a coordinate plane including a plurality of category information and a plurality of adjective information belonging to the plurality of categories;
specifying a position of the first index on the coordinate plane by using a coordinate value of the first index among the plurality of indexes;
selecting a category corresponding to the first index based on the location of the first index;
selecting one or more adjectives from among adjectives belonging to the selected category based on the coordinate value of the first index; and
and determining an adjective selected for each of the plurality of indices as an adjective corresponding to the facial mood of the user.
According to claim 1,
The step of determining the features of the face,
obtaining a reference point group designating each facial feature;
determining a positional relationship between reference points corresponding to a reference point group; and
A method for providing a platform for diagnosing facial mood using an image, comprising: defining a feature shape based on the determined result.
According to claim 1,
The step of selecting one or more adjectives,
Based on the adjectives included in the selected category, at least one adjective among a representative adjective that best matches the facial mood of the user, a reinforcing adjective that enhances the facial mood of the user, and a supplementary adjective that complements the facial mood of the user A method for providing a platform for diagnosing a facial mood using an image, comprising: determining a.
delete According to claim 1,
A method for providing a platform for diagnosing facial mood using images, including selecting a category located closest to the location of the first index.
According to claim 5,
The step of selecting one or more adjectives,
extracting adjectives corresponding to the selected category; and
A method for providing a platform for diagnosing facial mood using images, comprising: selecting an adjective whose x value or y value satisfies a specific criterion according to the characteristics of the selected category from among the extracted adjectives.
According to claim 6,
The step of selecting one or more adjectives,
arranging the order of the extracted adjectives in the order of having coordinate values of positions close to the coordinate values of the first exponent among the extracted adjectives;
selecting representative adjectives based on the order of the adjectives; and
A method of providing a platform for diagnosing facial mood using images, comprising: selecting at least one of adjectives up to a specific rank and representative adjectives among the adjectives in the order.
According to claim 6,
Calculating x-values and y-values that are symmetrical about the x-axis, the y-axis, and the origin based on the x- and y-values of the selected adjective;
selecting a category located closest to coordinate values corresponding to the calculated x and y values; and
Providing an adjective corresponding to the selected category as a supplementary adjective that complements the user's facial mood.
According to claim 1,
obtaining clothing information from a shopping mall;
extracting a mood of clothing based on the clothing information; and
Providing the user with clothing of an atmosphere suitable for the user; including,
A method for providing a facial mood diagnosis platform using images.
a memory that stores one or more instructions; and
a processor to execute the one or more instructions stored in the memory;
By executing the one or more instructions, the processor:
An apparatus that performs the method of claim 1 .
A computer program stored in a computer-readable recording medium to be combined with a computer, which is hardware, to perform the method of claim 1.

Images