KR101681501B1 - System and method for creating face avatar - Google Patents

Abstract

The present invention relates to an avatar face generating system and a method thereof. The method comprises the following steps of: displaying an image including a face on a user terminal; enabling the user terminal to extract a face portion image from the image; and enabling the user terminal to insert the extracted face portion image into image content.

Description

TECHNICAL FIELD [0001] The present invention relates to an avatar face generation system,

The present invention relates to an avatar face generation system and method, and more particularly, to an avatar face generation system and method for extracting a face portion image and forming a facial expression on the extracted facial portion image.

An avatar is an animated character that replaces the role of a user in online games, chatting, and virtual space. It started to be actively introduced with the Internet in the 1990s. In the 2000s, It is used in services such as Second Life and Lineage.

 The development of computer graphics technology has enabled avatars to be more realistic in terms of human body expressions. They are actively used mainly in films and CFs. In recent years, synergy effects of computer graphics technology and computer vision technology, sensor technology and computing hardware Actual human body avatars that can express the physical appearance and movement of real users due to development are being actively researched and applied to industries.

On the other hand, users want to create their own avatars, and the desire to have an avatar that reflects the characteristics of the user, rather than an avatar completely separate from the user, is also increasing.

However, there is a problem that the face of the avatar is limited to a single expression.

Korean Registered Patent No. 10-1629219 (Registered on Mar. 23, 2016)

It is an object of the present invention to provide an avatar face generation system and method capable of providing avatar face portion images of various facial expressions.

It is another object of the present invention to provide a system and method for generating an avatar face that can form facial part images of various facial expressions using one facial part image.

A method for generating an avatar face according to an exemplary embodiment of the present invention includes: displaying an image including a face on a user terminal; The user terminal extracting a face portion image from the image; And inserting the facial part image extracted by the user terminal into the image content.

In addition, the step of the user terminal extracting the face portion image from the image includes: recognizing the user's touch on the image including the face; Determining if the user terminal forms the closed interval of the user's touch; And extracting a face portion image from the user terminal in the closed interval.

In addition, the step of inserting the facial part image extracted by the user terminal into the image content may include: forming a lattice on the facial part image extracted by the user terminal; Distorting a portion of the grid formed in the face portion image such that the user terminal can form at least one of the facial portion image of laughter, sadness, anger and surprise; Correcting the distorted face portion image of the user terminal; And inserting the facial portion image corrected by the user terminal into the image content.

The step of distorting a portion of the grid formed in the face portion image such that the user terminal can form at least one of a face image, a laugh, a sadness, an angry face, and a surprise, And receiving reference facial expression information; And distorting a part of the grid formed on the facial image using the reference facial expression image and the reference facial expression information.

The step of distorting a part of the lattice formed on the facial part image using the reference facial expression image and the reference facial expression information may further comprise the steps of: Comparing; And distorting the face portion image corresponding to the grid formed on the face portion image different from the grid formed in the reference facial image using the reference facial expression information.

The step of distorting using the reference facial expression information may include performing distortion for forming a facial expression on the face partial image by the number of the reference facial expression information, obtaining an average value of the performed distortions, It may correspond to a step of distortion using an average value.

Also, the step of distorting using the reference facial expression information may correspond to a step of calculating the average degree of distortion of the plurality of identical facial expression information collected and distorting based on the calculated average degree of distortion.

In addition, after the step of inserting the facial part image into the image content, a predetermined corresponding one of the predetermined types of facial expressions is selected according to the click, swipe input of the user terminal, or user touching of the crisis object around the image of the face part on the screen And outputting a facial expression.

In addition, after the step of inserting the facial part image into the image content, the image content in which the facial part image is inserted is inserted into a part of the electronic still image book, and a predetermined facial expression change according to the page content of the electronic story book is output, And outputting the predetermined facial expression among the predetermined types of facial expressions according to the contact.

An avatar generation system according to an embodiment of the present invention includes a user terminal for extracting a face portion image from an image including a face and forming a face on the extracted face portion image; And a server for transmitting a reference facial expression image and reference facial expression information so that the user terminal can form a facial expression on the facial partial image, wherein the user terminal comprises: a face extraction module for extracting the facial part image; And a facial expression forming module for forming a facial expression on the facial part image extracted by the facial expression extracting module, wherein the facial expression forming module comprises: a lattice forming module for forming a lattice on the extracted facial part image; An image distortion module for distorting a part of the grating formed on the face portion image by the grating forming module to form a facial expression; And a correction module for correcting the facial part image distorted by the image distortion module.

According to the avatar face generation system and method of the present invention, an avatar face portion image having various facial expressions can be provided.

In addition, there is an effect that a facial part image having various facial expressions can be formed by using one facial part image.

In addition, there is an effect that a face part image formed with various facial expressions can be stored in a server.

In addition, there is an effect that a face partial image stored in the server can be shared by various devices.

In addition, there is an effect that the face of the avatar is formed by various face part images of the user, thereby enhancing the immersion feeling for the content used by the user.

1 is a diagram illustrating an avatar face generation system according to an embodiment of the present invention.
2 is a diagram showing a configuration of a user terminal.
3 is a diagram showing the configuration of the facial expression forming module.
4 is a view showing a state where a lattice is formed on a facial part image.
FIG. 5 is a view showing a reference facial image for forming a smiling facial expression by distorting a part of a lattice formed on a facial part image.
6 is a view showing a reference facial image for forming a sad facial expression by distorting a part of a lattice formed on a facial part image.
7 is a view showing reference expression information for forming an angular expression by distorting a part of a lattice formed on a facial part image.
8 is a view showing reference expression information for forming a surprised expression by distorting a part of the lattice formed in the facial part image.
FIG. 9 is a flowchart illustrating an avatar face generation method according to an embodiment of the present invention.
FIGS. 10 to 14 are views showing a combination of a face part image and image content generated according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. The following examples are intended to illustrate the present invention and should not be construed as limiting the scope of the present invention. Accordingly, equivalent inventions performing the same functions as the present invention are also within the scope of the present invention.

In the following description, the same reference numerals denote the same components, and unnecessary redundant explanations and descriptions of known technologies will be omitted.

In the embodiment of the present invention, 'communication', 'communication network' and 'network' can be used in the same sense. The three terms refer to wired and wireless local area and wide area data transmission and reception networks capable of transmitting and receiving a file between a user terminal, a terminal of another user, and a download server.

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

1 is a diagram illustrating an avatar face generation system according to an embodiment of the present invention.

Referring to FIG. 1, an avatar face generation system 10 includes a user terminal 100 and a server 200.

The user terminal 100 and the server 200 communicate with each other via a network including the Internet.

The user terminal 100 may correspond to a mobile device including a smart phone, a tablet, and a notebook, but the scope of the present invention is not limited thereto and may correspond to a non-mobile device such as a desktop.

The user terminal 100 may download an application for performing the avatar face generation method from the server 200. [

The user terminal 100 may operate in conjunction with the server 200 and may transmit the facial image generated by the user terminal 100 to the server 200. [

For this, a predetermined application for operating in conjunction with the server 200 must be previously set in the user terminal 100 according to an embodiment of the present invention.

The application may be defined as a client program installed in the user terminal 100 in order to perform the avatar face creation method through the user terminal 100 in cooperation with the server 200 have.

The server 200 may provide an application for performing an avatar face generation method to the user terminal 100, may store the facial part image transmitted by the user terminal 100, and may request the facial part image stored It can be transmitted to various devices.

When the facial image extracted from the user terminal 100 is corrected, the server 200 determines whether the facial shape of the specific model including the elliptical shape, inverted triangle, rhombus, inverted pentagon, And stored as face type information.

The server 200 may store the transformation data for correcting the shape of the facial portion image so as not to damage the original shape of the facial portion image and to be close to the elliptical shape.

When the user terminal 100 distorts a part of the lattice formed on the facial part image to form a facial part image, the server 200 must distort the lattice in order to form a facial expression such as smile expression, sad expression, And stores the reference facial image as a criterion of whether facial expression or surprise facial expression is obtained.

The server 200 acquires the big data of the facial expression information expressed in the images and generates the reference facial expression information which is a reference of the degree of lattice distortion using the obtained big data.

The server 200 can generate reference expression information based on the shapes of the eyes and mouths expressed in the images included in the big data and the shapes of eyes and mouths of the individuals represented in the images are different, The reference facial expression information can be generated. That is, the server 200 may generate and store a plurality of reference expression information.

The server 200 may store the facial part image transmitted from the user terminal 100. [ The stored facial image may be transmitted to various devices of the user including the user terminal 100.

The server 200 may store image contents information to be transmitted to the user terminal 100. Here, the image content information includes a main screen theme, an avatar setting screen, a play screen (for example, a vocational play, a car play, etc.), a moving picture screen (for example, a popular fairy tale, ), And a photo zone screen (e.g., a toe animation photo zone, etc.), but the present invention is not limited thereto. Any image that can be displayed on the user terminal 100 can be image content information.

The server 200 may be a server of the present invention if a cloud server is suitable but is not limited thereto and data collection, storage, management, and transmission are possible.

As used herein, the term " server " refers to a logical building block, and is not necessarily a physically distinct component. It is obvious to those skilled in the art to which the present invention belongs.

2 is a diagram showing a configuration of a user terminal.

2, the user terminal 100 includes a control module 110, a display module 120, a face extraction module 130, a facial expression forming module 140, a communication module 150, and a database 160 do.

The control module 110 controls the overall operation of the user terminal 100 and manages the operation of the application installed in the user terminal 100.

The user can operate the overall operation of the user terminal 100 using input means such as a key pad, a dome switch, a touch pad (static pressure / static electricity), and a jog wheel included in the control module 110 And manage the operation of the application installed in the user terminal 100. [

The control module 110 manages the overall information about the avatar face generation system 10 subscription of the user and the avatar face generation system 10 provided to the user. The user provides basic personal information for subscription to the avatar face generation system 10 to the server 200 through the user terminal 100 and provides basic personal information for subscription to the avatar face generation system 10 after subscription to the avatar face generation system 10. [ Set scope and permissions. For example, the control module 110 can manage whether or not the user transmits the facial partial image generated by the user terminal 100 to the server 200 according to an embodiment of the present invention.

Such information is managed as login information for each user, and the control module 110 stores the login information in a database 160 described later. The login information includes personal information of the user and identification information of the user terminal 100 held by the user.

The display module 120 displays the facial part image, the image content information, and the face part image generated by the facial expression forming module 140 described below in the database 160, which will be described later.

The display module 120 recognizes whether the user terminal 100 is touched and if it is determined that the touch associated with the application installed in the user terminal 100 (for example, touching the icon displayed on the display module 120) Thereby activating an application installed in the server 100. [

Also, the display module 120 recognizes whether or not the user touches the displayed image when an image including a face is displayed on the display module 120.

When the image including the face is displayed on the display module 120, the display module 120 contacts the image displayed on the display module 120 over a predetermined period of time to move up or down or left and right, Or when the user's touch forms a closed section on the image displayed on the display module 120, the predetermined section touched by the user or the closed section formed by the user's touch is referred to as a face section .

The face extraction module 130 extracts a face portion image from the face portion determined by the display module 120 using an application installed in the user terminal 100. [

The face extraction module 130 can correct the face portion image in a general face form when the extracted face portion image is different from a common face shape. At this time, the face extraction module 130 receives the reference face type information as a general face type reference from the server 200 through the communication module 150, which is described later, Can be corrected.

The face extraction module 130 determines whether or not the extracted face image is an ellipse, an inverted triangle, a rhombus, an inverted pentagon, and a rectangle, which are reference face type information, And the face type of the specific model including the model. For example, if it is determined to be an elliptical shape, no correction is performed. If it is determined to be one of an inverted triangle, a rhombus, an inverted pentagon, and a rectangle, the server 200 searches the extracted facial region image for an elliptical shape, The facial part image is corrected using the conversion data stored in the facial part image.

The facial expression forming module 140 may be configured to receive a facial image from the server 200 using the application installed in the user terminal 100 so that the communication module 150, The face portion image is distorted using the reference facial expression information.

The facial expression forming module 140 generates a facial part image in which the facial part image is formed by distorting the facial part image so that a facial expression is formed on the facial part image extracted by the facial expression extraction module 130. [

The extent to which the facial expression forming module 140 distorts the face portion image to form a facial expression is determined using the reference facial expression information stored in the server 200. [

The method in which the facial expression forming module 140 distorts the facial part image to form a facial expression does not distort the facial part image at one time to form a facial expression, but rather performs distortion to form a facial expression in the facial part image several times And obtains an average value of the distortion performed, and uses the obtained average value of the distortion to distort the face portion image. For example, the reference facial expression information for forming a facial expression in the facial part image may be stored in the server 200, and distortion for forming a facial expression in the facial part image by the number of reference facial expression information . Accordingly, the facial expression forming module 140 may obtain an average value of the distortions performed on the face portion image, and may distort the face portion image using the obtained mean value of the distortion.

The communication module 150 enables communication between the user terminal 100 and the server 200.

 The communication module 150 transmits the facial part image generated by the facial expression forming module 140 to the server 200.

The communication module 150 receives the image of the face portion previously stored in the server 200 transmitted by the server 200.

The communication module 150 receives the image content information transmitted by the server 200.

The communication module 150 receives the reference face type information transmitted by the server 200.

The communication module 150 receives the reference facial expression image and reference facial expression information transmitted from the server 200. [

The database 160 stores login information for each user managed by the control module 110.

The database 160 includes a face part image extracted by the face extraction module 130, an image of a face part generated by the facial expression forming module 140, an image of a face part transmitted from the server 200, the reference facial expression image and the reference facial expression information transmitted from the server 200, and the reference facial type information transmitted from the server 200. [

FIG. 3 is a view showing a configuration of a facial expression forming module, FIG. 4 is a view showing a state where a grid is formed on an image of a face part, FIG. 5 is a diagram showing a reference for forming a smiling face by distorting a part of a grid formed on a face part image 6 is a view showing a reference facial image for forming a sad facial expression by distorting a part of a lattice formed on a facial part image, and Fig. 7 is a view showing a reference facial image for distorting a part of the lattice formed in the facial part image, FIG. 8 is a view showing a reference facial image for forming a surprising facial expression by distorting a part of a lattice formed in a facial part image.

Referring to FIG. 3, the facial expression module 140 includes a lattice-forming module 142, an image distortion module 144, and a correction module 146.

3 and 4, the lattice-forming module 142 forms a lattice in the facial part image extracted and corrected by the face extracting module 130. [

The grating formed by the grating forming module 142 may have a square shape, but is not limited thereto. If a grating having a certain rule can be formed on the facial portion image, a grating such as a net shape, a circle shape, a triangle shape and a rhombus may be formed It is also possible to do.

The number of gratings formed by the grating forming module 142 is preferably 30, but the present invention is not limited thereto. The image distortion module 144, which will be described later, may distort the facial part image and form a lattice The number of gratings is more or less at least.

The grating formed by the grating forming module 142 may form a grating with vertical and horizontal lines. However, if the grating having a certain rule can be formed in the facial portion image, a grating may be formed with left and right slant lines .

4 and 5 to 8, the image distortion module 144 may generate the image of the facial part formed by the grid forming module 142 using the reference facial image and the reference facial expression information received from the server 200 The image of the face portion corresponding to some of the gratings is distorted.

The characters S11, S12, etc. expressed in the lattice of Figs. 4 to 8 indicate the position of the lattice, and when the characters indicating the position of the lattice are the same, they denote the lattice at the same position in Figs.

Referring to FIGS. 4 and 5, in order to see that the image distortion module 144 distorts the facial part image to form a smiling face, The reference facial image of FIG. 4A differs from the facial portion image of the inside of the grid of FIG.

5 is a reference facial image for displaying a smiling facial expression. Therefore, the face facial image inside the lattice of FIG. 4 is different from the reference facial image of FIG. 5 in the S31, S32, S34, S35, S52, S53, If the image is distorted as shown in the reference facial image shown in Fig. That is, the lattice formed on the facial part image corresponding to S31, S32, S34 and S35 of Fig. 4 is distorted such that the lower part of the lattice is directed upward, The grating formed on the partial image can form a facial portion image of a smiling face if the gratings are distorted such that the top of the grating is directed downward.

S32, S34, S35, S52, S53, and S54 of FIG. 6 to see that the image distortion module 144 distorts the facial portion image to form a sad expression. Referring to FIGS. 4 and 6, The reference facial image of FIG. 4A differs from the facial portion image of the inside of the grid of FIG.

6, S31, S32, S34, S35, S52, S53 and S54 of FIG. 4 which are different from the reference facial image in the grid of FIG. 6 because they are reference facial images for displaying sad facial expressions, If the image is distorted as shown in the reference facial image, it is possible to form a face image of a sad facial expression. That is, the grid formed on the face portion image corresponding to S31, S32, S34, and S35 of FIG. 4 is obtained by distorting the grid such that the upper portion and the lower portion of the grid face the center portion, The lattice formed on the face portion image corresponding to S34 and S35 is distorted in the clockwise direction.

In addition, the lattice formed on the facial part image corresponding to S52, S53, and S54 of Fig. 4 can form a sad facial facial part image if the lattices are distorted such that the lower part of the lattice is directed upward.

S32, S34, S35, S52, S53, and S54 of FIG. 7 to see that the image distortion module 144 distorts the facial portion image to form an angry look. Referring to FIGS. 4 and 7, The reference facial image of FIG. 4A differs from the facial portion image of the inside of the grid of FIG.

7 is S31, S32, S34, S35, S52, S53 and S54 of FIG. 4, which are different from the reference facial image in the grid of FIG. 7 because it is a reference facial expression image for displaying an angry facial expression. If the image is distorted as shown in the reference facial image, it is possible to form the facial part image of the angry facial expression. That is, the grid formed on the face portion image corresponding to S31, S32, S34, and S35 of FIG. 4 is obtained by distorting the grid such that the upper portion and the lower portion of the grid face the center portion, And the lattice formed on the facial part image corresponding to S34 and S35 is distorted in the counterclockwise direction.

In addition, if the grids formed in the face portion image corresponding to S52, S53, and S54 in FIG. 4 are distorted such that the upper and lower portions of the grating face the middle portions, an image of a face portion of an angry face can be formed.

Referring to FIGS. 4 and 8, in order to see that the image distortion module 144 distorts the facial part image to form a surprised facial image, The reference facial image of FIG. 4A differs from the facial portion image of the inside of the grid of FIG.

8 is a reference facial image for showing a surprised facial expression, the facial part image in the lattice of S31, S32, S34, S35, S52, S53 and S54 in Fig. 4, which is different from the reference facial image in Fig. 8, If the image is distorted as shown in the reference facial image shown in Fig. That is, the grids formed in the facial portion images corresponding to S31, S32, S34, and S35 of FIG. 4 expand the upper and lower portions of the grating to distort the grating so as to be closer to a circle.

In addition, the lattice formed on the facial part image corresponding to S52, S53 and S54 of Fig. 4 can form a surprising facial image by distorting the lattice such that the upper part and the lower part of the lattice are expanded to be closer to the circular shape .

The extent to which the image distortion module 144 distorts the face portion image to form a facial expression is determined using the reference facial expression information stored in the server 200. [

The image distortion module 144 distorts the facial part image to form a facial expression. The facial part image is distorted at one time to form a facial image, but the facial part image is distorted to form a facial image on the facial part image many times And obtains an average value of the distortion performed, and uses the obtained average value of the distortion to distort the face portion image. For example, the reference facial expression information for forming a facial expression in the facial part image may be stored in the server 200, and distortion for forming a facial expression in the facial part image by the number of reference facial expression information . Accordingly, the image distortion module 144 may obtain an average value of the distortions performed on the face portion image, and may distort the face portion image using the obtained mean value of the distortion.

Specifically, referring to FIGS. 4 and 5, the image distortion module 144 may be distorted for eye and mouth facial expressions, and for this purpose, the eye and mouth are located and set. In the case of Fig. 4, s31, 32, s34 and 35 correspond to the eyes, and s52, 53 and 54 correspond to the eyes. The distortion of the relevant part is set to be, and for the degree of distortion, the corresponding part is distorted several times (eg, 100 times or more), and then an average value of the distortion is taken, and the final distortion can be achieved.

Here, the distortion may be generally obtained by taking an average value of degrees of distortion of a plurality of corresponding facial expressions (for example, sadness) collected in the past.

The correction module 146 corrects the distorted facial portion image by the image distortion module 144. [

Correction module 146 is distorted by the image distortion module 144 such that the surrounding lattice of the distorted grating also appears natural.

The correction module 146 performs correction to fill the blank margin with the same color as the face color when a blank margin occurs in the face portion image.

Correction module 146 may perform a correction to fill the mouth interior with an image within the standard mouth if the facial part image is an open mouth image.

The correction module 146 may perform a correction to align the protruded portion with the outline line of the face image when the protruded portion exists in the outline line of the face portion image.

As used herein, the term " module " refers to a logical building block, and is not necessarily a physically distinct component, as is apparent to those skilled in the art.

FIG. 9 is a flowchart illustrating a method of generating an avatar face according to an embodiment of the present invention. FIGS. 10 to 14 illustrate a combined face portion image and image content generated according to an embodiment of the present invention to be.

Referring to FIG. 9, an image displaying a face on the user terminal is displayed (S900).

Here, an image in which a face is displayed may be an image in which a face is emphasized as in an ID photo, but the present invention is not limited thereto, and any image can be used as long as it is an image in which a face is displayed and a face can be recognized.

The user terminal recognizes whether the user touches the terminal (S910).

Here, if the image including the face is displayed on the display module 120, the display module 120 of the user terminal 100 recognizes whether the displayed image is touched by the user.

If the user's touch forms a closed section, the closed section is determined as a face section (S920).

In this case, when the image including the face is displayed on the display module 120, the display module 120 of the user terminal 100 contacts the image displayed on the display module 120 for a predetermined time or longer When the user touches a predetermined area or more, or when the user's touch forms a closed section on the image displayed on the display module 120, the predetermined area or the touch of the user touched by the user in the image is formed And determines the closed section as the facial part.

If it is determined in the user terminal 100 that the facial portion is present, the facial portion image is extracted from the closed section (S930).

At this time, the face extraction module 130 of the user terminal 100 extracts the face part image from the face part determined by the display module 120 using the application installed in the user terminal 100.

The face extraction module 130 of the user terminal 100 can correct the face portion image in a general face form when the extracted face portion image is different from a common face shape. At this time, the face extraction module 130 receives reference face type information as a general face type reference from the server 200 through the communication module 150, and corrects the face part image using the reference face type information can do.

A grid is formed on the extracted facial part image (S940).

At this time, the grid formation module 142 of the user terminal 100 forms a grid on the facial part image extracted and corrected by the face extraction module 130.

Some of the lattices are distorted so that the extracted face portion image forms a facial expression (S950).

At this time, the image distortion module 144 of the user terminal 100 uses the reference facial expression image and the reference facial expression information received from the server 200 to generate facial features corresponding to a part of the lattice formed by the lattice- Distort the image.

The distorted face portion image is corrected (S960).

The correction module 146 of the user terminal 100 corrects the distorted facial portion image by the image distortion module 144. [

The image content is displayed on the user terminal, and the corrected face portion image is inserted into the character face portion of the displayed image content (S970).

10 to 14, FIG. 10 shows a combined image of a face part generated according to an exemplary embodiment of the present invention on a main screen having a theme, and FIG. 11 shows an example of a face image generated according to an embodiment of the present invention And displays the screen for setting the avatar using the facial part image.

Referring to FIG. 10, the corrected face portion image may be a face image of a user's click, swipe input, or a preset facial expression among various types of facial expressions preset according to the contact of a crisis object, such as a bus, Can be output.

FIG. 12 is a view showing a combined image of a face part generated according to an embodiment of the present invention on a play screen such as a work play, a car play, and the like. FIG. FIG. 14 is a view showing an example of a combined image of a face image generated according to an embodiment of the present invention, and FIG. 14 is a view showing a combined image of a face image generated according to an embodiment of the present invention, .

In addition, the corrected face portion image may be inserted into a portion of the electronic still book to output a predetermined facial expression change according to the contents of the electronic still book, and at this time, a change output may be performed according to the user's click, swipe, .

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments. That is, within the scope of the present invention, all of the components may be selectively coupled to at least one.

In addition, although all of the components may be implemented as one independent hardware, some or all of the components may be selectively combined to perform a part or all of the functions in one or a plurality of hardware. As shown in FIG. The codes and code segments constituting the computer program may be easily deduced by those skilled in the art.

Such a computer program can be stored in a computer-readable storage medium, readable and executed by a computer, thereby realizing an embodiment of the present invention. As a storage medium of the computer program, a magnetic recording medium, an optical recording medium, or the like can be included.

It is also to be understood that the terms such as " comprises, "" comprising," or "having ", as used herein, mean that a component can be implanted unless specifically stated to the contrary. But should be construed as including other elements.

All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used terms, such as predefined terms, should be interpreted to be consistent with the contextual meanings of the related art, and are not to be construed as ideal or overly formal, unless expressly defined to the contrary.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention.

Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

100 .... user terminal
110 .... control module
120 .... display module
130 .... Facial Extraction Module
140 .... facial expression forming module
150 .... Communication module
160 .... database
200 .... server

Claims (10)

Displaying an image including a face of a user terminal;
The user terminal extracting a face portion image from the image; And
Inserting the face portion image from which the user terminal is extracted into the image content,
Wherein the step of inserting the facial part image extracted by the user terminal into the image content comprises:
Forming a grid on the face portion image from which the user terminal is extracted;
Distorting an image corresponding to a portion of a grid formed in the face portion image such that the user terminal can form a face image of one of laughter, sadness, anger and surprise;
Correcting the distorted face portion image of the user terminal; And
Inserting the facial part image corrected by the user terminal into the image content,
The step of distorting the image corresponding to a portion of the grid formed on the face portion image such that the user terminal can form a facial image of one of laughing, sadness, anger and surprise,
Receiving a reference facial expression image and reference facial expression information related to facial expressions of laughter, sadness, anger, and surprise from a server; And
And distorting an image corresponding to a part of the grid formed on the facial part image using the reference facial expression image and the reference facial expression information,
Wherein the step of distorting an image corresponding to a part of the grid formed on the facial part image using the reference facial expression image and the reference facial expression information,
The user terminal comparing the in-grid image formed on the reference facial image with the in-grid image formed on the facial feature image; And
The user terminal distorting the in-grid image formed on the face partial image different from the in-grid image formed on the reference facial image using the reference facial expression information,
Distorting an in-grid image formed on the face portion image different from an in-grid image formed on the reference facial image using the reference facial expression information, the user terminal comprising:
The image is distorted so that the lower part of the image in the lattice corresponding to the eyes of the face is directed to the upper side of the face so that the facial part image forms a smiling face and the upper part of the lattice image corresponding to the mouth of the face is facial Distorting the image so as to face downward;
The image is distorted such that the upper and lower portions of the image in the grid corresponding to the eyes of the face are directed to the lower and upper sides of the face, respectively, so that the face portion image forms a sad expression, Distorting the image so that the image rotates counterclockwise, distorting the image so that the image in the grid corresponding to the left eye of the face rotates clockwise, and the lower part of the image in the grid corresponding to the mouth of the face, Distorting the image so as to face upward;
The image is distorted such that the upper and lower portions of the in-grid image corresponding to the eyes of the face are directed to the lower and upper sides of the face, respectively, so that the facial portion image forms an angry facial expression, Distort the image so that my image rotates clockwise, distort the image so that the image in the grid corresponding to the left eye of the face rotates counterclockwise, and the top and bottom of the image in the grid corresponding to the mouth of the face Distorting the image so as to face the lower and upper sides of the face, respectively; And
The image is distorted so that the upper and lower portions of the image in the grid corresponding to the eyes of the face are directed to the upper and lower sides of the face, respectively, so that the face portion image forms a surprised expression, And distorting the image such that the top and bottom portions of the image are directed upward and downward, respectively, of the face. The method according to claim 1,
Wherein the step of the user terminal extracting a face portion image from the image comprises:
Recognizing a user's touch on the image including a face by a user terminal;
Determining if the user terminal forms the closed interval of the user's touch; And
The user terminal extracts a face part image in the closed interval
And generating an avatar face image. delete delete delete The method according to claim 1,
Wherein the step of distorting using the reference facial expression information comprises:
Performing distortion to form a facial expression on the facial part image by the number of the reference facial expression information, obtaining an average value of the performed distortions, and distorting the obtained average using the obtained average value of the distortions
The face of the avatar is generated. The method according to claim 1,
Wherein the step of distorting using the reference facial expression information comprises:
Calculating the average degree of distortion of the plurality of identical facial expression information collected and distorting based on the calculated average degree of distortion
The face of the avatar is generated. The method according to claim 6,
After inserting the facial part image into the image content,
Outputting a predetermined facial expression among a plurality of predetermined facial expressions according to a click, a swipe input of a user terminal, or a user touch contact of a crisis object around the face partial image on the screen
And generating an avatar face image. The method according to claim 6,
After inserting the facial part image into the image content,
The image content in which the face part image is inserted is inserted into a part of the electronic still book so that a preset facial expression change according to the page contents of the electronic story book is outputted and outputted or a predetermined facial expression among various kinds of facial expressions preset according to the user touch Step for output
And generating an avatar face image. A user terminal for extracting a face portion image from an image including a face and forming a face on the extracted face portion image,
The user terminal comprises:
A face extraction module for extracting the face portion image; And
And a facial expression forming module for forming facial expressions on the facial part image extracted by the face extracting module,
The facial expression forming module includes:
A grid forming module for forming a grid in the extracted facial part image;
An image distortion module for distorting the image corresponding to a part of the grid formed in the face portion image such that the face portion image forms a face of laughter, sadness, angryness and surprise; And
And a correction module for correcting the image of the face part distorted by the image distortion module,
The user terminal receives a reference facial expression image and reference facial expression information regarding a facial expression of laughter, sadness, anger, and surprise from a server,
A reference facial expression image and a reference facial expression information, the image corresponding to a part of the lattice formed on the facial part image is distorted,
Said image distortion module comprising:
Compares an in-grid image formed on the reference facial expression image with an in-grid image formed on the face partial image,
Wherein the reference image is generated by using the reference facial expression information,
The image is distorted so that the lower part of the image in the lattice corresponding to the eyes of the face is directed to the upper side of the face so that the facial part image forms a smiling face and the upper part of the lattice image corresponding to the mouth of the face is facial Distort the image so that it faces downward,
The image is distorted such that the upper and lower portions of the image in the grid corresponding to the eyes of the face are directed to the lower and upper sides of the face, respectively, so that the face portion image forms a sad expression, Distorting the image so that the image rotates counterclockwise, distorting the image so that the image in the grid corresponding to the left eye of the face rotates clockwise, and the lower part of the image in the grid corresponding to the mouth of the face, Distort the image to face upward,
The image is distorted such that the upper and lower portions of the in-grid image corresponding to the eyes of the face are directed to the lower and upper sides of the face, respectively, so that the facial portion image forms an angry facial expression, Distort the image so that my image rotates clockwise, distort the image so that the image in the grid corresponding to the left eye of the face rotates counterclockwise, and the top and bottom of the image in the grid corresponding to the mouth of the face Distort the image to face down and up, respectively, of the face, and
The image is distorted so that the upper and lower portions of the image in the grid corresponding to the eyes of the face are directed to the upper and lower sides of the face, respectively, so that the face portion image forms a surprised expression, An avatar face generation system that distorts the image so that the top and bottom portions of the image face upward and downward, respectively.

Images