KR102109818B1 - Method and apparatus for processing face image - Google Patents

Abstract

The face image processing method performed in the disclosed face image processing apparatus comprises: modeling a standard face to generate standard face mesh data including a plurality of meshes and facial expression data for the standard face mesh data, and targeting an image for an arbitrary user Extracting a plurality of feature points present in the face region in the image, transforming standard face mesh data based on the plurality of feature points to generate personal face mesh data, and transforming information between the standard face mesh data and the personal face mesh data And correcting facial expression data based on the.

Description

METHOD AND APPARATUS FOR PROCESSING FACE IMAGE}

The present invention relates to a face image processing method and apparatus, and more particularly, to a face image processing method and apparatus for changing a facial expression in an image.

There are many methods of human communication. One of them is facial expression. The other party in communication can grasp the speaker's emotions or intentions from the speaker's facial expression.

The communication method using facial expressions can be applied to virtual characters appearing in movies or animations. That is, the viewer can grasp information such as the emotion or intention of the character or the surrounding situation from the facial expression of the character. Furthermore, a service can be provided by replacing the face part of the character with the face image of the spectator, and in this case, the immersion of the spectator is improved as the face of the character appears in the movie or animation.

However, in the case of replacing the face portion of a character in a video object such as a movie or animation with a face image of an arbitrary user, unlike the general retargeting technique, the expression of the face image inserted in the video object can be naturally changed. Technology is required.

Republic of Korea Patent Publication No. 10-2018-0070688, published date of June 26, 2018.

According to an embodiment of the present invention, there is provided a face image processing method and apparatus for correcting a facial expression in an image in consideration of personal characteristics of a face to be serviced.

In addition, a face image processing method and apparatus for correcting a facial expression in an image for each region are provided.

The problem to be solved of the present invention is not limited to those mentioned above, and another problem to be solved that is not mentioned will be clearly understood by those having ordinary knowledge to which the present invention belongs from the following description.

According to a first aspect of the present invention, a face image processing method performed in a face image processing apparatus includes modeling a standard face to generate standard face mesh data including a plurality of meshes and facial expression data for the standard face mesh data. ; Extracting a plurality of feature points present in a face region in the image, targeting an image for an arbitrary user; Generating personal face mesh data by modifying the standard face mesh data based on the plurality of feature points; And correcting the facial expression data based on deformation information between the standard face mesh data and the personal face mesh data.

In the computer program according to the second aspect of the present invention, instructions for performing each step according to the face image processing method are recorded on a computer-readable recording medium.

A face image processing apparatus according to a third aspect of the present invention includes a modeling unit for modeling a standard face to generate standard face mesh data including a plurality of meshes, and to generate facial expression data for the standard face mesh data; An image processing unit for extracting a plurality of feature points present in a face region in the image, for an image for an arbitrary user; And a personalization processing unit that generates personal face mesh data by transforming the standard face mesh data based on the plurality of feature points, and corrects the facial expression data based on deformation information between the standard face mesh data and the personal face mesh data. do.

According to an exemplary embodiment of the present invention, the facial expression in the image may be corrected for each part by considering personal characteristics of the face to be serviced or corrected for each part, thereby preventing an expression distortion caused by a characteristic difference between the standard face and the service face.

1 is a block diagram of a facial image processing apparatus according to an embodiment of the present invention.
2 to 4 are flowcharts for explaining a face image processing method using a face image processing apparatus according to an embodiment of the present invention.
5 to 11 illustrate various examples of face mesh data and service target face images that can be provided by performing a face image processing method in the face image processing apparatus according to an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them will be clarified with reference to embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various forms, and only these embodiments allow the disclosure of the present invention to be complete, and have ordinary knowledge in the art to which the present invention pertains. It is provided to fully inform the person of the scope of the invention, and the scope of the invention is only defined by the claims.

In describing the embodiments of the present invention, detailed descriptions of known functions or configurations will be omitted except when necessary in describing the embodiments of the present invention. In addition, terms to be described later are terms defined in consideration of functions in an embodiment of the present invention, which may vary according to a user's or operator's intention or practice. Therefore, the definition should be made based on the contents throughout this specification.

1 is a block diagram of a facial image processing apparatus according to an embodiment of the present invention.

As shown in FIG. 1, the facial image processing apparatus 100 according to an embodiment includes a modeling unit 110, an image processing unit 120, and a personalization processing unit 130.

The modeling unit 110 models standard faces to generate standard face mesh data including a plurality of meshes. In addition, the modeling unit 110 may generate facial expression data for standard face mesh data. For example, the modeling unit 110 may generate a plurality of blend shapes to generate facial expression data. The blend shape is the distance and direction values of the target that the vertices should move within the mesh.

The image processing unit 120 extracts a plurality of feature points present in a face region in the image, targeting an image for an arbitrary user. For example, the image processing unit 120 may use a known facial landmark detection algorithm.

The personalization processing unit 130 generates personal face mesh data by transforming the standard face mesh data based on a plurality of feature points extracted by the image processing unit 120. Then, the personalization processing unit 130 separates the face portion from the image including the face to be serviced based on the personal face mesh data. In addition, the personalization processing unit 130 may generate facial expression data of the personal facial mesh data based on facial expression data of the standard facial mesh data. Here, when generating facial expression data of personal face mesh data, the personalization processing unit 130 acquires deformation information between the standard and the individual to prevent facial expression distortion. That is, when transforming the standard face mesh data into personal face mesh data, deformation information indicating a difference value between two face mesh data is acquired. Subsequently, the personalization processing unit 130 generates facial expression data corrected by the deformation information based on the deformation information between the standard and the individual in generating the facial expression data of the personal facial mesh data based on the facial expression data of the standard facial mesh data. That is, the blend shape is corrected by the personalization processing unit 130 in proportion to the deformation information between the standard and the individual.

Further, the personalization processing unit 130 moves the vertices constituting the mesh of the standard face mesh data to positions of a plurality of feature points extracted from an image for an arbitrary user when the standard face mesh data is modified to generate the personal face mesh data. Personal face mesh data can also be generated by rigging a face bone including a plurality of face construction points in the standard face mesh data, and then moving the plurality of face construction points to the locations of the plurality of feature points to thereby generate the personal face mesh data. You can also generate data. In this case, the personalization processing unit 130 may rig the vertices of the standard face mesh data to at least one face configuration point of the plurality of face configuration points, thereby generating standard face mesh data with face bones rigged. For example, the number of vertices and the number of face construction points included in the standard face mesh data may be the same, but is not limited thereto. In addition, the personalization processing unit 130 may rig at least two to four or less facial constituent points among a plurality of facial constituent points included in the facial bone.

As described above, the modeling unit 110, the image processing unit 120, and the personalization processing unit 130 constituting the facial image processing apparatus 100 according to an embodiment may each include a microprocessor, and their operations Will be explained in more detail below.

2 to 4 are flowcharts for explaining a face image processing method using a face image processing apparatus according to an embodiment of the present invention. In these flowcharts, an example in which a blend shape is produced as facial expression data is shown.

As shown in FIGS. 2 to 4, the face image processing method according to an embodiment includes modeling a standard face to generate standard face mesh data including a plurality of meshes (S201), and facial expressions for the standard face mesh data Generating data (S203), extracting a plurality of feature points present in a face portion of the image for an image for an arbitrary user (S205), modifying standard face mesh data based on the plurality of feature points to personal face The method includes generating mesh data (S207), obtaining deformation information between standard face mesh data and personal face mesh data (S209), and correcting facial expression data based on the obtained deformation information (S211).

Here, when acquiring deformation information between the standard and the individual, it is possible to obtain a rate of change between the size of the face outline of the standard face mesh data and the size of the face outline of the personal face mesh data, and when correcting the facial expression data, the rate of change between the face outline sizes Facial expression data can be corrected proportionally. Alternatively, when acquiring the deformation information between the standard and the individual, the standard face mesh data and the personal face mesh data are divided into a plurality of parts (S301), and then the deformation information is obtained for each of the plurality of parts (S303), and facial expression data is corrected. At this time, facial expression data may be corrected for each of a plurality of parts based on the obtained deformation information for each part (S305).

In addition, when generating personal face mesh data, face bones including a plurality of face construction points are generated and rigged in the standard face mesh data (S401), and the plurality of face construction points are moved based on the plurality of feature points to move the individual It can be transformed into face mesh data (S403).

Hereinafter, the processes of performing the face image processing method as shown in FIGS. 2 to 4 in the face image processing apparatus 100 according to an embodiment of the present invention shown in FIG. 1 are illustrated in FIGS. 5 to 11 Let's take a closer look with reference to various examples.

First, the modeling unit 110 of the face image processing apparatus 100 models a standard face to generate standard face mesh data including a plurality of meshes. As illustrated in FIG. 5, the modeling unit 110 may generate standard face mesh data 501 in which at least three vertices form one mesh (S201).

In addition, the modeling unit 110 may generate facial expression data for standard face mesh data. For example, the modeling unit 110 may generate a plurality of blend shapes 502, 503, 504, and 505 as illustrated in FIG. 5 to generate facial expression data (S203).

The image processing unit 120 of the face image processing apparatus 100 extracts a plurality of feature points present in a face portion of the image, targeting an image for a random user. As illustrated in FIG. 6, the image processing unit 120 may extract a plurality of feature points 602 of the service target face when the image 601 including the service target face is input. For example, the image processing unit 120 may use a known facial landmark detection algorithm. The facial feature point detection algorithm is a deep learning-based image processing technology, and can extract about 68 feature points by analyzing feature points such as the eyes, nose, mouth, and chin of the face (S205).

The personalization processing unit 130 of the face image processing apparatus 100 generates personal face mesh data in which standard face mesh data is modified based on a plurality of feature points extracted by the image processing unit 120. The personalization processing unit 130 may generate personal face mesh data 603 using standard face mesh data 501 as illustrated in FIG. 6. For example, an individual face in which the standard face mesh data 501 is transformed by moving and transforming vertices constituting the mesh of the standard face mesh data 507 to a plurality of feature point positions of the image 601 including the face to be serviced. The mesh data 603 may be generated (S207).

In addition, since the personalization processing unit 130 has generated facial expression data for the standard facial mesh data as described above, facial expression data of the personal facial mesh data may be generated based on the facial expression data of the standard facial mesh data. . As described above with reference to FIG. 5, the modeling unit 110 may generate facial expression data by manufacturing a plurality of blend shapes 502, 503, 504, and 505 for the standard face mesh data 501. In this case, the personalization processing unit 130 applies a plurality of blend shapes 502, 503, 504, and 505 to the personal face mesh data 603, as illustrated in FIG. 6, thereby blending the plurality of blend shapes 502, 503. , 504 and 505, a plurality of facial expression images including specific facial expression images 604 of the service target faces, respectively.

However, not only the shape of the face is not the same, but there are many differences. Different people have different face sizes, and the size of the eyes, nose, and mouth, which are the parts that make up the face, also varies. Therefore, if the expression data generated from the standard face is applied to the personal face as it is, the desired expression may not be properly expressed. In particular, there is a high possibility of distortion of facial expressions in areas where the density of the vertices constituting the mesh is relatively higher than other detailed areas such as the eye area and the mouth area. As illustrated in FIG. 7, when the normal personal face mesh data 701 and the abnormal personal face mesh data 702 are compared, it can be seen that a distorted phenomenon 703 occurs in the eye region, and thus the facial expression is distorted.

Therefore, the personalization processing unit 130 acquires standard and interpersonal deformation information when generating personal face mesh data in step S207 to prevent facial expression distortion. That is, when transforming the standard face mesh data into personal face mesh data, deformation information indicating a difference value between two face mesh data is acquired. For example, as illustrated in FIG. 8, the personalization processing unit 130 may obtain the size of the face outline of the standard face mesh data 801 and the rate of change of the face outline size period of the personal face mesh data 802 as deformation information. . For example, it is possible to obtain the rate of change in the outer contour period of the face by comparing the width and height of the face (S209).

Subsequently, in generating the facial expression data of the personal face mesh data based on the facial expression data generated in step S203, the personalization processing unit 130 corrects the facial expression data corrected by the deformation information based on the standard and interpersonal deformation information obtained in step S209. To create. That is, the blend shape is corrected by the personalization processing unit 130 in proportion to the deformation information between the standard and the individual. For example, if the face width of the personal face mesh data is 90% and the face height is 70% based on the face width and face height of the standard face mesh data, the blend shape target position of each position is 10% horizontally and vertically It can be reduced by 30% (S211).

In addition, the personalization processing unit 130 may correct the facial expression data for each part after dividing the face into a plurality of parts when correcting the facial expression data as in step S211. For example, the personalization processing unit 130 may divide the eye portion and the mouth portion of the detailed parts of the face into separate parts. In this case, the eye region and the mouth region may be divided based on a result of comparing the density of vertices constituting the mesh of the personal face mesh data with a preset reference value. For example, since the density of the mesh is higher than that of other regions, the eye region and the mouth region can be divided by separating only the region where the density of corrections is higher than a predetermined reference value. And, as illustrated in FIG. 9, the personalization processing unit 130 may obtain the rate of change in size between the eye region 901 of the standard face mesh data and the eye region 902 of the personal face mesh data as deformation information between the standard and the individual. , The rate of change in size between the mouth region 903 of the standard face mesh data and the eye region 904 of the personal face mesh data may be obtained as the standard and individual deformation information. For example, a size change rate may be obtained by comparing the width and height of the eye region and the mouth region (S303). Subsequently, the personalization processing unit 130 generates the facial expression data of the personal face mesh data based on the facial expression data generated in step S203, based on the standard obtained in step S303 and the plurality of partial deformation information between the individual parts. Facial expression data corrected for each part is generated as much as the transformation information for each star. That is, a blend shape corrected for each part is produced by the personalization processing unit 130 in proportion to the deformation information of a plurality of parts between the standard and the individual. For example, if the eye area width of the personal face mesh data is 95% and the eye area height is 90% based on the eye area width and the eye area height of the standard face mesh data, the blend shape target of each position in the area The position may be reduced by 5% horizontally and 10% vertically (S305).

10 is a facial expression 1001 reflecting the blend shape of the standard face mesh data as it is in the personal face mesh data, a facial expression 1002 corrected and reflected based on the rate of change of the outer contour size between the standard and the individual, and the eye region between the standard and the individual It is a comparison of facial expressions 1003 reflected and corrected for each part based on the rate of change in size and the rate of change in size of the mouth. It can be seen that facial expression distortion occurs in the facial expression 100, but facial expression distortion does not occur in the facial expression 1002 and the facial expression 1003. It can be seen that the facial expression 1003 exhibits a smoother facial expression change than the facial expression 1002.

Meanwhile, when the personalized face mesh data is generated in step S207, the personalization processing unit 130 may generate personalized face mesh data by rigging face bones to standard facial mesh data and then deforming it. For example, the personalization processing unit 130 rigs a facial bone including a plurality of facial constitution points 1101 in standard facial mesh data as illustrated in FIG. 11. Here, the personalization processing unit 130 may rig the vertices of the standard face mesh data to at least one face configuration point of the plurality of face configuration points 1101 to generate standard face mesh data 1102 with face bones rigged. have. For example, the number of vertices included in the standard face mesh data and the number of face construction points 1101 may be the same, but are not limited thereto. Also, the personalization processing unit 130 rigs at least two to four or less facial configuration points among the plurality of facial configuration points 1101 included in the facial bones. For example, rigging one vertex of the standard face mesh data to three facial construct points 1101 included in the facial bone means that the vertex depends on three facial construct points. How much one vertex depends on which facial constituent point among the plurality of facial constituent points can be represented by a weight, and the sum of the weights of one vertex is 1. For example, by rigging one vertex to three facial or four facial constituent points of the facial bone, the polygon deformation caused by the facial bone is smoothly displayed while the overlapping of polygons does not occur and the computation amount is excessive. It may be made not to rise (S401).

Then, the personalization processing unit 130 moves the plurality of facial configuration points based on the plurality of feature points extracted by the image processing unit 120 to generate personal face mesh data in which standard face mesh data is modified. As illustrated in FIG. 11, the personalization processing unit 130 may generate personal face mesh data using standard face mesh data 1102 rigged with face bones. For example, the personal face mesh data in which the standard face mesh data 1102 is transformed by moving and transforming a plurality of face constituting points of the standard face mesh data to a plurality of feature point positions of the image 601 including the face to be serviced ( 603) may be generated (S403).

According to an embodiment of the present invention as described so far, facial expression in the image is distorted by taking into account the personal characteristics of the face to be serviced or correcting for each part, thereby causing facial expression distortion due to a characteristic difference between the standard face and the face to be serviced. I never do that.

The combination of each block in the block diagram and each step of the flowchart attached to the present invention may be performed by computer program instructions. These computer program instructions may be mounted on a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, so that instructions executed through a processor of a computer or other programmable data processing equipment may be used in each block or flowchart of the block diagram. In each step, means are created to perform the functions described. These computer program instructions can also be stored in computer readable or computer readable memory that can be oriented to a computer or other programmable data processing equipment to implement a function in a particular way, so that computer readable or computer readable memory The instructions stored in it are also possible to produce an article of manufacture containing instructions means for performing the functions described in each step of each block or flowchart of the block diagram. Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so a series of operational steps are performed on a computer or other programmable data processing equipment to create a process that is executed by the computer to generate a computer or other programmable data. It is also possible for instructions to perform processing equipment to provide steps for performing the functions described in each block of the block diagram and in each step of the flowchart.

Further, each block or each step can represent a module, segment, or portion of code that includes one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative embodiments it is possible that the functions mentioned in blocks or steps occur out of order. For example, two blocks or steps shown in succession may in fact be executed substantially simultaneously, or it is also possible that the blocks or steps are sometimes performed in reverse order depending on the corresponding function.

The above description is merely illustrative of the technical idea of the present invention, and those of ordinary skill in the art to which the present invention pertains may make various modifications and variations without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the claims below, and all technical thoughts within the equivalent range should be interpreted as being included in the scope of the present invention.

According to an embodiment of the present invention, the facial expression in the image does not occur due to a characteristic difference between a standard face and a service target face by considering the personal characteristics of the service target face or by correcting each face.

The present invention can be applied to a technical field of service by replacing a face portion of an appearance in a video object such as a movie or animation with a face image of an arbitrary user.

100: face image processing device
110: modeling department
120: image processing unit
130: personalization processing unit

Claims (15)

A face image processing method performed in a face image processing apparatus,
Modeling a standard face to generate standard face mesh data including a plurality of meshes and facial expression data for the standard face mesh data;
Extracting a plurality of feature points present in a face region in the image, targeting an image for an arbitrary user;
Generating personal face mesh data by modifying the standard face mesh data based on the plurality of feature points;
Correcting the expression data based on deformation information between the standard face mesh data and the personal face mesh data; And
Generating facial expression data for the personal facial mesh data based on the facial expression data for the corrected standard facial mesh data;
The deformation information includes a rate of change between the face outline size of the standard face mesh data and the face outline size of the personal face mesh data,
The step of correcting the facial expression data may correct the facial expression data in proportion to the rate of change.
Face image processing method.
delete ◈ Claim 3 was abandoned when payment of the set registration fee was made.◈ According to claim 1,
The deformation information, after dividing the standard face mesh data and the personal face mesh data into a plurality of parts, includes deformation information obtained for each of the plurality of parts,
The correcting of the facial expression data may include correcting the facial expression data for each of the plurality of parts based on the obtained deformation information for each of the plurality of parts.
Face image processing method. ◈ Claim 4 was abandoned when payment of the set registration fee was made.◈ The method of claim 3,
When dividing into the plurality of parts, the eye or mouth part of the detailed parts of the face is divided into separate parts
Face image processing method. ◈ Claim 5 was abandoned when payment of the set registration fee was made.◈ The method of claim 4,
When dividing into the plurality of parts, the eye part or the mouth part is divided based on a result of comparing the density of vertices constituting the mesh with a predetermined reference value.
Face image processing method. A face image processing method performed in a face image processing apparatus,
Modeling a standard face to generate standard face mesh data including a plurality of meshes and facial expression data for the standard face mesh data;
Extracting a plurality of feature points present in a face region in the image, targeting an image for an arbitrary user;
Generating personal face mesh data by modifying the standard face mesh data based on the plurality of feature points;
Correcting the expression data based on deformation information between the standard face mesh data and the personal face mesh data; And
Generating facial expression data for the personal facial mesh data based on the facial expression data for the corrected standard facial mesh data;
The deformation information, after dividing the standard face mesh data and the personal face mesh data into a plurality of parts, includes deformation information obtained for each of the plurality of parts,
The correcting of the facial expression data includes correcting the facial expression data for each of the plurality of parts based on the obtained deformation information for each of the parts,
When dividing into the plurality of parts, the eye or mouth part of the detailed parts of the face is divided into separate parts,
The deformation information for each part includes a size change rate of the eye region or a size change ratio of the mouth region,
The correcting of the facial expression data may include correcting the facial expression data in proportion to the size change rate of the eye region or the size change ratio of the mouth region.
Face image processing method.
◈ Claim 7 was abandoned when payment of the set registration fee was made.◈ According to claim 1,
The generating of the personal face mesh data may include: generating face bones including a plurality of face constituting points and rigging the standard face mesh data; And
And moving the plurality of facial constitution points based on the plurality of feature points to transform the personal face mesh data.
Face image processing method. An instruction to perform each step according to the face image processing method according to any one of claims 1 to 3 to 7
A computer program recorded on a computer readable recording medium.
A modeling unit for modeling a standard face to generate standard face mesh data including a plurality of meshes, and to generate facial expression data for the standard face mesh data;
An image processing unit for extracting a plurality of feature points present in a face region in the image, for an image for an arbitrary user; And
The standard face mesh data is modified based on the plurality of feature points to generate personal face mesh data, and the facial expression data is corrected based on deformation information between the standard face mesh data and the personal face mesh data, and the corrected And a personalization processing unit that generates facial expression data for the personal facial mesh data based on facial expression data for standard facial mesh data,
The deformation information includes a rate of change between the face outline size of the standard face mesh data and the face outline size of the personal face mesh data,
The personalization processing unit corrects facial expression data for the standard face mesh data in proportion to the rate of change.
Face image processing device.
delete ◈ Claim 11 was abandoned when payment of the set registration fee was made.◈ The method of claim 9,
The personalization processing unit divides the standard face mesh data for the standard face mesh data and the personal face mesh data into a plurality of parts, acquires the deformation information for each of the plurality of parts, and obtains the deformation for each of the plurality of parts Correcting facial expression data for the standard face mesh data for each of the plurality of parts based on information
Face image processing device. ◈ Claim 12 was abandoned when payment of the set registration fee was made.◈ The method of claim 11,
The personalization processing unit divides the eye area or the mouth area into separate parts of the detailed parts of the face
Face image processing device. ◈ Claim 13 was abandoned when payment of the registration fee was set.◈ The method of claim 12,
The personalization processing unit divides the eye region or the mouth region based on a result of comparing the density of vertices constituting the mesh with a preset reference value.
Face image processing device. A modeling unit for modeling a standard face to generate standard face mesh data including a plurality of meshes, and to generate facial expression data for the standard face mesh data;
An image processing unit for extracting a plurality of feature points present in a face region in the image, for an image for an arbitrary user; And
The standard face mesh data is modified based on the plurality of feature points to generate personal face mesh data, and the facial expression data is corrected based on deformation information between the standard face mesh data and the personal face mesh data, and the corrected And a personalization processing unit that generates facial expression data for the personal facial mesh data based on facial expression data for standard facial mesh data,
The personalization processing unit divides the standard face mesh data for the standard face mesh data and the personal face mesh data into a plurality of parts, acquires the deformation information for each of the plurality of parts, and obtains the deformation for each of the plurality of parts Correction of facial expression data for the standard face mesh data for each of the plurality of parts based on information,
The personalization processing unit divides the eye area or the mouth area of the detailed parts of the face into separate parts,
The deformation information for each part includes a size change rate of the eye region or a size change ratio of the mouth region,
The personalization processing unit corrects facial expression data for the standard face mesh data in proportion to the size change rate of the eye area or the size change rate of the mouth area
Face image processing device. ◈ Claim 15 was abandoned when payment of the set registration fee was made.◈ The method of claim 9 or 14,
The personalization processing unit generates a facial bone including a plurality of facial configuration points, rigging the standard facial mesh data, and moving the plurality of facial configuration points based on the plurality of feature points to move the personal facial mesh Transformed into data
Face image processing device.

Images