JP2001216531A - Method for displaying participant in three-dimensional virtual space and three-dimensional virtual space display device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To remarkably improve visibility to specify an operator (participant) himself or herself from his or her alter ego displayed in a three-dimensional virtual space while keeping a proper data communication volume in a three- dimensional virtual space system where many users communicate with each other through a communication line to share the three-dimensional virtual space constructed by using CG techniques. SOLUTION: A device is provided with a synthetic face picture generation means (a face area extraction part 12, a template face picture selection and face area correction part 13, a template face correction part 14, and a synthetic face generation part 15) which generates a three-dimensional and stereoscopic synthetic face picture on the basis of an actually photographed face picture, a model selection part 16 which makes the operator select one from preliminarily prepared face skeleton models hair models respectively, and a data transmission part 17 which transmits the synthetic face picture, the identifier of the selected face skeleton model, and that of the selected hair model to the other users sharing the virtual space through a communication line 4.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a computer graphics (CG) technique in which a large number of users (participants) use computer terminals and communicate with each other via a communication line. The present invention relates to a three-dimensional virtual space system that shares a constructed three-dimensional virtual space, in particular, by displaying a self-imposed alteration created in the virtual space based on a face image of an operator who is a participant. The present invention relates to a three-dimensional virtual space participant display method and a three-dimensional virtual space device capable of increasing the degree of recognition of users in a virtual space.

[0002]

2. Description of the Related Art In a three-dimensional virtual space, as a technique for displaying an operator who is a user of the three-dimensional virtual space, conventionally, an image captured so as to include the whole body of the operator is directly displayed in the virtual space. Attach an image containing the face of the operator to a human-like CG model, such as the method of displaying in, or the avatar in “Interspace (http://cybersociety.elcs.intsp.or.jp/)” There is a way to display.

[0003] Further, a method of creating a three-dimensional CG model imitating a specific person is disclosed in US Vitana Corpo.
"ShapaGrabber (ht
tp: //www.vitana.com/) ”, there is a method using a three-dimensional digitizer.

[0004]

An application of a three-dimensional virtual space system in which a plurality of participants and users share a three-dimensional virtual space via a communication line includes a virtual mall opened on a network. . In an application such as a virtual mall, an authentication method for identifying the operator is required when purchasing a product, giving and receiving money, performing settlement, and the like. When using a three-dimensional virtual space system, a CG that is an alter ego of the operator displayed in the virtual space
When considering identity authentication from the model, the alter ego of the current similar system is not sufficiently expressive to be able to authenticate.

[0005] Further, when simply communicating using the three-dimensional virtual space system, if the whole body or face image of the operator is displayed in the virtual space,
When the distance to the opponent in the virtual space is long, or when the opponent is not facing the opponent, it is difficult to specify the opponent as the communication target from among the large number of participants.

CG created using a three-dimensional digitizer
In the method of displaying a model in virtual space, since this method aims to faithfully generate an object existing in real space as an object (virtual object) in virtual space, it takes time to generate a virtual object. Therefore, the data amount of the created virtual object is often not suitable for the purpose of sending it to the other party via the communication line. Further, since the three-dimensional digitizer uses a special device, it is not suitable for general use of a three-dimensional virtual space display device using a general personal computer.

SUMMARY OF THE INVENTION It is an object of the present invention to significantly improve the visibility of specifying an individual from an alternation of an operator (participant) displayed in a three-dimensional virtual space while maintaining an appropriate data communication amount as a communication system. It is an object of the present invention to provide a three-dimensional virtual space participant display method and apparatus.

[0008]

SUMMARY OF THE INVENTION According to the present invention, there is provided a three-dimensional C-like image resembling an operator from an image including the operator's face taken from the front.
Generating a G face model and displaying it on a computer terminal of another user in the three-dimensional virtual space is performed using a general-purpose imaging device and display device.

That is, the three-dimensional virtual space participant display method of the present invention combines the three-dimensional CG torso model with the three-dimensional CG face model created from the photographed face image of the operator's face. In a three-dimensional virtual space participant display method for displaying in a virtual space, a step of creating a three-dimensional and three-dimensional composite face image based on a real face image of the face of the operator, The method includes a step of causing the operator to select one of the face skeleton models, and a step of causing the operator to select one of the prepared hair models.

According to the present invention, when a synthetic face image is created in this way and the operator selects a face skeleton model and a hair model, the synthesized face image, an identifier for specifying the selected face skeleton model, The identifier specifying the selected hair model may be transmitted to another user sharing the three-dimensional virtual space. Users who receive these data,
The face image is pasted on the face skeleton model corresponding to the received face skeleton model identifier, and a three-dimensional CG face model is created by combining the face image with the hair model corresponding to the received hair model identifier. By displaying in combination, the three-dimensional CG model of the operator who transmitted the data can be displayed in the three-dimensional virtual space displayed on the display screen of the user.

After all, according to the present invention, a face image of an operator photographed from the front using a commercially available inexpensive camera which can be connected to a general-purpose computer terminal represented by a personal computer (personal computer) is also obtained. At the same time, it becomes possible to create and display a three-dimensional CG face model using a prepared hair model and a face skeleton model. This allows
This enables automation and real-time processing of creating a three-dimensional CG face model with a reduced amount of data.

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, a preferred embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a processing mechanism of a three-dimensional virtual space display device according to one embodiment of the present invention.

The three-dimensional virtual space display device 1 is roughly divided into two processing mechanisms: an operator model creation unit 2 and a participant display unit 3.

An operator model creating section 2 creates a three-dimensional CG model imitating the operator from an image of the operator,
A processing unit for transmitting, via the communication line 4, data necessary for displaying the alter ego of the operator in the virtual space to a three-dimensional virtual space display device operated by another participant in the three-dimensional virtual space. The face image photographing section 11 and the face area extracting section 1
2, a template face image selection / face area correction unit 13, a template face correction unit 14, a composite face creation unit 15, a model selection unit 16, and a data transmission unit 17.

The face image photographing section 11 is for photographing a face image of the operator, and comprises a video camera or the like. The face area extracting unit 12 extracts only the image of the face area from the face image captured by the face image capturing unit 11. In the following description, the image of the face area is simply referred to as a face area. The template face image selection / face area correction unit 13
In order to select one from a plurality of template face images prepared in advance and to display the face area extracted by the face area extraction unit 12 straight (to display the face facing directly), The position of the face area is corrected by rotating the face area, and the image of the extracted face area is vertically oriented so that the positions of the eyes and mouth of the selected template face image coincide with the positions of the eyes and mouth of the face area. And / or expands and contracts laterally. Here, the template face image is a base when the face region is pasted to the skeleton model of the face, and is an image viewed not only from the front but also from the entire circumference such as right, left, and back. Multiple types are prepared according to the characteristics of women, fat faces, and thin faces.

The template face correction unit 14 calculates an average value of colors in the face area extracted by the face area extraction unit 12,
The face color of the template face image is adjusted so that the value becomes equal to the average value of the face color of the template face image. The composite face creation unit 15 creates a composite face image by superimposing the face area corrected by the template face image selection / face area correction unit 13 on the template face image whose face color has been corrected by the template face correction unit 14. .

The model selection unit 16 allows the operator to select a skeleton model and a hair model of the face used by the three-dimensional CG human model displayed as the alter ego of the operator in the virtual space. The data transmission unit 17 communicates via the communication line 4
The combined face image, the identifier for specifying the skeleton model of the selected face, and the identifier for specifying the selected hair model are transmitted to the participant display unit 3 of the three-dimensional virtual space display device of another user.

On the other hand, the participant display unit 3 is provided with a copy of each operator based on data transmitted via the communication line 4 from the operator model creation unit 2 in another three-dimensional virtual space display device. This is a processing unit for displaying the three-dimensional CG model on the three-dimensional virtual space display device 1, and includes a data receiving unit 18 and another person model display unit 19.

The data receiving unit 18 specifies the data (the synthesized face image, the identifier for specifying the face skeleton model, and the hair model) transmitted from the operator model generating unit 2 of the other user's three-dimensional virtual space display device. Identifier). The other person model display unit 19 reads the corresponding face skeleton model stored in the own device from the identifier for specifying the face skeleton model in the received data, and reads the received face model from the identifier for specifying the hair model. , Read out the corresponding hair model stored in, and combine these models with the received synthetic face image to construct a three-dimensional CG human model and display it on the screen.

FIG. 2 is a diagram for explaining a situation where a plurality of participants observe a virtual space using the three-dimensional virtual space display device. Here, an example is shown in which the number of participants is three (operators 5A to 5C).

3 used by each of the operators 5A to 5C
The three-dimensional virtual space display devices 1A to 1C are mutually connected via a communication line 4. Before participating in the virtual space, each operator creates a three-dimensional CG human model that resembles himself,
Data necessary for displaying the data is transmitted to the three-dimensional virtual space display device of the participant who has already participated in the virtual space. If a participant already exists in the virtual space at the time of joining the virtual space, a request is made to the three-dimensional virtual space display device of the participant to transmit a three-dimensional CG person model of each operator. Receive. The person models 7A to 7C, which are the alter egos of each participant, are displayed on each device based on the spatial positional relationship in the virtual space 6. The person models 7A to 7C correspond to the operators 5A to 5C, respectively.

By exchanging the three-dimensional CG person model in this manner, the display screen 8A of the three-dimensional virtual space display device 1A of the operator 5A displays the person model (self-body) corresponding to each of the operators 5B and 5C. 7B and 7C are displayed. Display screens 8B, 8 of other operators 5B, 5C
Also in C, the person models of the participants (operators) excluding themselves are displayed.

FIG. 3 is a diagram showing a three-dimensional virtual space display device constituted by using a personal computer (personal computer) as a general-purpose computer system and the surroundings. When a personal computer or the like is used, the three-dimensional virtual space display device functions as a computer terminal (operator terminal) of the three-dimensional virtual space system.

The operator 5 can observe the state of the three-dimensional virtual space via the display device (display) 21 of the computer system. In addition, a camera 22 for photographing an operator's face image before participating in the three-dimensional virtual space is installed on the display device 21. Further, in order to allow the operator 5 to select a template face image and a face skeleton model or a hair model, a keyboard 23 and a mouse 24 are used as input devices.
Is provided.

FIG. 4 is a block diagram showing a system configuration of a computer system for configuring a three-dimensional virtual space display device.

The computer system includes a display device 21 for displaying a virtual space to the operator, a camera 22 for photographing the operator, a keyboard 23 and a mouse 24 as input devices, and a central device. Processing unit (CPU) 3
1, a hard disk device 32 for storing programs and data, a main memory 33, a communication interface 34 serving as a connection unit for a communication line, a magnetic tape or a CD-ROM.
A reading device 36 for reading a recording medium 37 such as a ROM. Display device 21, camera 22, keyboard 23, mouse 24, hard disk device 32, main memory 33, communication interface 34, and reading device 36
Are connected to the central processing unit 31.

In this computer, a recording medium 37 storing a program for performing the three-dimensional virtual space participant display method described in this embodiment is mounted on a reading device 36,
The program is read from the recording medium 37, stored in the hard disk device 32, and the central processing unit 31 executes the program stored in the hard disk device 32, thereby functioning as the above-described three-dimensional virtual space display device.

Next, the details of the operation of the three-dimensional virtual space display apparatus of this embodiment will be described.

FIG. 5 is a diagram for explaining the processing of the face area extraction unit 12. As shown in FIG. 5A, generally, the original image 41 captured so as to include the operator's face includes a background and clothing worn by the operator in addition to the operator's face. Assuming that the captured image is a color image based on the RGB color system, in order to extract only the face region from this image, the RGB color system of the image is converted into the YIQ color system, and the channels of both color systems are converted. By combining the features and setting a threshold value, only a region considered to be flesh color is extracted. Eye,
Since the eyebrows, mouth, and the like are not displayed in the skin color and are not included in this area, the area included in the extracted skin color area is also extracted as the face area. As shown in FIG. 5B, the extracted area 42 includes a face area and its components, and does not include hair.

FIG. 6 is a diagram showing the processing of the template face image selection / face area correction unit 13. First, the operator specifies the positions of the eyes and the position of the mouth, and performs image processing so that the heights of the eyes are equal by rotating the extracted face region with reference to the positions. FIG. 6A shows an image 51 after such image processing has been performed.

On the other hand, the operator selects a template face image. FIG. 6B shows an example of the template face image 52. As shown, the template face image 52 includes an image of a texture (a uniform pattern), eyes, eyebrows,
This is an image where facial components such as the nose and mouth are pasted.
This is for pasting to the dimensional CG face skeleton model.
By including a texture image, the template face image 52 is also called a template texture. Since the template face image 52 is attached to the entire periphery of the head of the face skeleton model, it looks as if the constituent components of the face have been stretched at a special scale. Also, the template face image 52
Is previously created so as to be suitable for the unevenness of the face when pasted on the skeleton model, and the positions of the eyes and the mouth are checked in advance. Then, the distance between the eyes and the distance between the eyes and the mouth of the extracted face area image 51 are the distance 53 between the eyes and the distance between the eyes and the mouth 5 of the template face image 52.
The image 51 is expanded and contracted in the vertical and horizontal directions so as to be equal to 4, respectively, and an image 55 after deformation is created as shown in FIG.

The details of the processing by the template face image selection / face area correction unit 13 have been described above.

FIG. 6 is a diagram showing the processing of the composite face creating section 15. The composite face creation unit 15 creates a composite face image from the template face image 52 and the transformed face image 55 described above. First, the brightness of the face image 55 is changed to the template face image 5
The brightness of the face image 55 is adjusted so as to be equal to the average value of the brightness of No. 2. Thereafter, in order to make the synthesized boundary inconspicuous, a gradient is applied to the boundary of the face image 55 by a predetermined distance, and the color of the template face image 52 is changed outward from the center. However, when the color is changed, the color may be different depending on the position of the boundary of the face image. For example, in the synthetic face image 61, when the pixel 62 at the forehead portion of the extracted face area boundary is compared with the pixel 64 at the cheek portion of the extracted face area boundary, the cheek tends to be a shadow at the time of shooting, and the forehead is not illuminated. Since it is easy to hit, it is considered that the brightness of the pixel 62 is higher. Therefore, it is assumed that a method of applying a gradient is determined for each position of the boundary with reference to the color at that position. That is, when the color at the position of the pixel 64 is expressed by the RGB color system, the red, green, and blue components are R (x ₆₄ , y ₆₄ ), G
For the color at the position of (x ₆₄ , y ₆₄ ), B (x ₆₄ , y ₆₄ ), pixel 65 (a pixel on the straight line connecting the center of the image and the pixel 64 and outside the pixel 64), R (x _65, y _55), G
Expressed as (x ₆₅ , y ₆₅ ) and B (x ₆₅ , y ₆₅ ), a red component R (x, y) of a point (x, y) on a straight line connecting the pixel 64 and the pixel 65
y), a green component G (x, y), and a blue component B (x, y)

[0034]

(Equation 1)

## EQU3 ## The line segment 66 connects the pixel 64 and the pixel 65. Pixel 62 and Pixel 63
Similarly, the color of a point on a straight line connecting the center of the image and the pixel 62 and outside the pixel 62 is determined. Thus, a composite face image is created.

FIG. 7 shows a screen (model selection window) displayed by the model selection unit 16 to the operator via the display device.
71 is shown. The model selection unit 16 holds a plurality of face skeleton models, their identifiers, a plurality of hair models, and their identifiers. The face skeleton model and hair model
Both are CG models. The operator selects one face skeleton model from the face model list 72 using a mouse or the like, and selects one hair model from the hair model list 73. Schematic diagrams of the selected models are displayed in a face model schematic display window 74 and a hair model schematic display window 75, respectively. The model selection unit 16 outputs an identifier indicating the face model selected by the operator and an identifier indicating the selected hair model.

Through the above processing, the identifier for identifying the operator himself, the created composite face image, the identifier of the selected facial skeleton model, and the identifier of the selected hair model are stored in the data. The data is transmitted from the transmission unit 17 to the participant display unit 3 of the three-dimensional virtual space display device used by another user of the virtual space.

When data is transmitted from the data transmission unit 17 of another three-dimensional virtual space display device, the data reception unit 18 of the participant display unit 3 receives the data and transmits the received data to the operator. The identifier, the identifier of the face skeleton model, the identifier of the hair model, and the composite face image are divided and passed to the other person model display unit 19. The other person model display unit 19 is based on the received face skeleton model identifier and hair model identifier from the face skeleton model and the hair model registered in advance in the computer system provided with the other person model display unit 19. Then, the face skeleton model and the hair model to be displayed are specified. A three-dimensional CG face model is generated by pasting the synthesized face image on the face skeleton model and further applying the hair model. Then, after reading out a model necessary for displaying a person in a virtual space such as a torso portion of the person model, the combined face image, face skeleton model, hair model, etc. are combined and displayed in the displayed virtual space. .

[0039]

As described above, according to the present invention, in a three-dimensional virtual space system, the amount of data to be transmitted to other participants in order to create a three-dimensional CG face model is not increased, and a special There is an effect that a three-dimensional CG face model that resembles the operator himself can be created without requiring any device. Further, by using a three-dimensional CG face model created based on the face image of the operator in the virtual space, the visibility of the operator from a long distance and a wide angle is improved.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a processing mechanism of a three-dimensional virtual space display device according to an embodiment of the present invention.

FIG. 2 is a diagram illustrating a situation in which a plurality of participants observe a virtual space using a three-dimensional virtual space display device.

FIG. 3 is a diagram showing a three-dimensional virtual space display device and a state around it.

FIG. 4 is a block diagram showing a system configuration of a computer system constituting the three-dimensional virtual space display device.

FIGS. 5A and 5B are diagrams for explaining the processing of a face area extracting unit;

FIGS. 6A to 6C show template face image selection and
FIG. 9 is a diagram for describing processing of a face area correction unit.

FIG. 7 is a diagram illustrating processing of a synthetic face creating unit.

FIG. 8 is a diagram illustrating an example of a screen displayed by a model selection unit to an operator.

[Description of Signs] 1, 1A to 1C 3D virtual space display device 2 Operator model creation unit 3 Participant display unit 4 Communication line 5, 5A to 5C Operator 6 Virtual space 7A to 7C Person model 8A to 8C Display screen Reference Signs List 11 face image photographing section 12 face area extracting section 13 template face image selecting / face area correcting section 14 template face correcting section 15 synthetic face creating section 16 model selecting section 17 data transmitting section 18 data receiving section 19 other person model displaying section 21 display Apparatus 22 Camera 23 Keyboard 24 Mouse 31 Central processing unit (CPU) 32 Hard disk drive 33 Main memory 34 Communication interface 36 Reading device 37 Recording medium 41 Original image photographed to include operator's face 42 Extracted area 51 Rotation Corrected face area image 52 Template face image 55 Face image after deformation Image 61 Synthetic face image 62 to 65 pixels 71 Model selection window 72 Face model list 73 Hair model list 74 Face model outline display window 75 Hair model outline display window

Claims (13)

[Claims] 1. A three-dimensional virtual space that displays an alter ego of the operator in a virtual space by synthesizing a three-dimensional CG body model with a three-dimensional CG face model created from a photographed face image of an operator's face. In the participant display method, three-dimensional,
Creating a three-dimensional synthetic face image; allowing the operator to select one of the prepared face skeleton models; and providing the operator with one of the prepared hair models. Selecting a three-dimensional virtual space participant display method. 2. A step of creating a three-dimensional and three-dimensional composite face image based on a photographed face image of the operator's face, extracting a skin color region from the photographed face image of the operator photographed from the front. And extracting the face image from the photographed face image by combining the skin color area and the area included in the skin color area as a face image, and causing the operator to specify the position of both eyes and the position of the mouth, Correcting the position in the extracted face image with reference to the position, the position of both eyes and the position of the mouth in one template face image selected from the template face image prepared in advance,
Extending and contracting the corrected face image vertically and / or horizontally so as to match the position of both eyes and the position of the mouth in the corrected face image, respectively; The method of claim 1, further comprising: creating a composite face image by superimposing the selected face images. 3. adjusting the brightness of the extracted face image so that the brightness of the extracted face image is equal to the average value of the brightness of the template face image; Changing the color of the template face image outward from the center by applying a gradient by a predetermined distance, and for each position of the boundary between the extracted face image and the template face image, 3. The method of displaying a participant in the three-dimensional virtual space according to claim 2, further comprising: determining a method of applying a gradient by determining the color of the participant. 4. The method according to claim 1, further comprising the step of: pasting a synthetic face image to the selected face skeleton model and combining it with the selected hair model to create a three-dimensional face model. 3. A three-dimensional virtual space participant display method according to item 1. 5. A three-dimensional virtual space system in which a plurality of participants respectively use a computer terminal and communicate via a communication line, and each participant shares a three-dimensional virtual space displayed on the computer terminal. In the three-dimensional virtual space participant display method for displaying each participant, the three-dimensional virtual space participant display method according to any one of claims 1 to 3, which relates to the operator who is the participant. And then transmitting the synthesized face image, the identifier of the selected face skeleton model, and the identifier of the selected hair model to other participants via the communication line, and receiving the synthesized face image, the face skeleton received Displaying a three-dimensional CG whole body model accompanied by the operator's face image on the computer terminal of the other participant based on the model identifier and the hair model identifier. 3D virtual space participant display method. 6. A three-dimensional CG body model combined with a three-dimensional CG face model created from a photographed face image of an operator's face to display an alter ego of the operator in a virtual space. A virtual space display device, comprising: a synthetic face image creating means for creating a three-dimensional and three-dimensional synthetic face image based on a real face image of the operator's face, and a face skeleton model prepared in advance. A model selection unit that allows the operator to select one of the hair models from among the prepared hair models, and another user sharing the virtual space via a communication line A data transmission unit for transmitting the composite face image, the identifier of the selected facial skeleton model, and the identifier of the selected hair model. 7. A combined face image, a face skeleton model identifier, and a hair model identifier are received via a communication line, and the combined face image is pasted to a face skeleton model corresponding to the received face skeleton model identifier. 7. The three-dimensional virtual space display apparatus according to claim 6, further comprising a participant display unit for creating and displaying a three-dimensional face model in combination with a hair model corresponding to the received hair model identifier. 8. A synthetic face image creating means for extracting a skin color region from a photographed face image of an operator photographed from the front, and extracting the skin color region and a region included in the skin color region as a face image. A face region extracting unit that allows the operator to select one of template face images prepared in advance, and specifies the positions of both eyes and the mouth in the extracted face image, and refers to the positions. To correct the position in the extracted face image,
Further, the corrected face image is vertically oriented such that the position of both eyes and the position of the mouth in the selected template face image respectively match the position of both eyes and the position of the mouth in the corrected face image. And / or a template face image selection / face area correction unit that expands / contracts in the horizontal direction, and a composite face creation unit that creates a composite face image by superimposing the contracted face image on the selected template face image. Item 3. The three-dimensional virtual space display device according to item 6 or 7. 9. The combined face image creating means further adjusts the brightness of the extracted face image so that the brightness of the extracted face image is equal to the average value of the brightness of the template face image. A gradient of a predetermined distance from the boundary of the extracted face image to change the color of the template face image from the center toward the outside, and the position of the boundary between the extracted face image and the template face image 9. The three-dimensional virtual space display device according to claim 8, further comprising a template face correction unit that determines a color of the position at each position and determines a method of giving a gradient. 10. A recording medium readable by a computer, comprising: synthesizing a three-dimensional CG body model with a three-dimensional CG face model created from a photographed face image of an operator's face; In order to display the image in the virtual space, the computer generates a three-dimensional image based on a photographed face image of the operator's face.
Creating a three-dimensional synthetic face image; allowing the operator to select one of the prepared face skeleton models; and providing the operator with one of the prepared hair models. A recording medium storing a program for executing the step of selecting. 11. A step of creating a three-dimensional and three-dimensional composite face image based on a photographed face image of the operator's face, extracting a skin color region from the photographed face image of the operator photographed from the front. And extracting the face image from the photographed face image by combining the skin color area and the area included in the skin color area as a face image, and causing the operator to specify the position of both eyes and the position of the mouth, Correcting the position in the extracted face image with reference to the position, the position of both eyes and the position of the mouth in one template face image selected from the template face image prepared in advance,
Extending and contracting the corrected face image vertically and / or horizontally so as to match the position of both eyes and the position of the mouth in the corrected face image, respectively; 11. The recording medium according to claim 10, further comprising: creating a composite face image by overlapping the selected face images. 12. The program according to claim 12, wherein the program adjusts the brightness of the extracted face image so that the brightness of the extracted face image is equal to the average value of the brightness of the template face image. Changing the color of the template face image outward from the center by applying a gradient by a predetermined distance from the boundary of the extracted face image, and changing the color of the extracted face image and the template face image. Determining for each boundary position the color at that position to determine how to apply the gradient.
A recording medium according to claim 1. 13. The program further causes the computer to execute a step of creating a three-dimensional face model by pasting a synthetic face image on a selected face skeleton model and combining the synthesized face image with the selected hair model. , Claim 1
13. The recording medium according to any one of 0 to 12.