JP2013196172A - Skin shape model generation device, skin shape model generation method, and skin shape model generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To realize quantitative shape simulation for which the shape of a face and the shape of texture are taken into consideration.SOLUTION: A skin shape model generation device for generating a three-dimensional skin shape using a skin shape generated by a prescribed parameter includes: pore generation means for generating a plurality of pores arranged in a prescribed distribution to a preset skin area; area division means for dividing the skin area by connecting the adjacent pores with each other among the plurality of generated pores; crista cutis and skin groove determination means for determining the shapes of a crista cutis and a skin groove for a division area; polygon generation means for generating a polygon of a prescribed shape on the basis of the shape of the pore generated by the pore generation means and the respective shapes of the crista cutis and the skin groove determined by the crista cutis and skin groove determination means; texture shape modeling means for modeling the texture shape of the skin by parameter information obtained by the shape of the polygon; and skin shape modeling means for generating a skin shape model by mapping the skin shape obtained by the texture shape modeling means corresponding to the part of a prescribed three-dimensional shape.

Description

  The present invention relates to a skin shape model generation device, a skin shape model generation method, and a skin shape model generation program.

  Conventionally, a method of reproducing a human face shape, for example, using a CG (Computer Graphics) model or the like is known. In this case, the shape of the skin, such as texture and pores, which are micro shapes, is expressed by texture mapping that creates a two-dimensional image that feels as if the skin is uneven, and is applied to the face shape polygon ( For example, refer nonpatent literature 1).

P. S. Heckbert, Survey of Texture Mapping, IEEE Computer Graphics and Applications, Volume 6, Issue 11, pages 56-67, 1986. Heckbert, Survey of Texture Mapping, IEEE Computer Graphics and Applications, Volume 6, Issue 11, pages 56-67.

  However, in the conventional method as described above, the three-dimensional unevenness of the actual skin is not reproduced. For this reason, for example, when performing a face light reflection simulation using a CG model, the influence of changes in pore size and skin depth is often not considered.

  Here, for example, an actual human face shape can be converted into polygon data by a three-dimensional laser scanner or the like, but even in this case, there is nothing that can simultaneously measure a micro shape such as a texture. In other words, conventionally, there is no method for simultaneously expressing a micro texture shape and a macro face shape, and only the degree of influence of color can be examined in the conventional texture and makeup skin simulations.

  The present invention has been made in view of the above problems, and generates a skin shape model that takes into account the shape of the texture and the three-dimensional shape of the face, hands, etc., and realizes a quantitative shape simulation. An object is to provide a skin shape model generation device, a skin shape model generation method, and a skin shape model generation program.

  In order to achieve the above-described object, the present invention is a skin shape model generation device that generates a three-dimensional skin shape using a skin shape generated according to a predetermined parameter. Pore generating means for generating a plurality of pores arranged in a predetermined distribution, and area dividing means for connecting adjacent pores among the plurality of pores generated by the pore generating means to divide the skin area; , A cuticle skin groove determining means for determining the shape of the skin and the skin groove for the region obtained by the region dividing means, the shape of the pore generated by the pore generating means, and the skin skin groove determining Polygon generating means for generating a polygon of a predetermined shape based on the shapes of the skin and the skin groove determined by the means, and parameter information obtained by the polygon shape obtained by the polygon generating means. A texture shape modeling means for modeling the texture shape of the skin, and a skin shape that generates a skin shape model by mapping the skin shape obtained by the texture shape modeling means corresponding to a predetermined three-dimensional shape portion And a modeling means.

  Further, the present invention is a skin shape model generation method for generating a three-dimensional skin shape using a skin shape generated by a predetermined parameter, and is arranged in a predetermined distribution with respect to a preset skin region Obtained by a pore generating step for generating a plurality of pores, an area dividing step for connecting adjacent pores among the plurality of pores generated by the pore generating step, and dividing the skin region, and the region dividing step A cuticle skin groove determining step for determining a shape of a skin and a skin groove for a given region, a shape of a pore generated by the pore generating step, and a skin bed determined by the skin mound skin groove determining step A polygon generation step for generating a polygon having a predetermined shape based on each shape of the skin groove, and a polygon obtained by the polygon shape obtained by the polygon generation step. A texture shape modeling step for modeling the texture shape of the skin based on the meter information, and a skin shape model generated by mapping the skin shape obtained by the texture shape modeling step in correspondence with a predetermined three-dimensional shape portion And a skin shape modeling step.

  Furthermore, the present invention is a skin shape model generation program for causing a computer to function as each unit included in the above-described skin shape model generation device.

  In addition, what applied the component, expression, or arbitrary combination of the component of this invention to a method, an apparatus, a system, a computer program, a recording medium, a data structure, etc. is also effective as an aspect of this invention.

  ADVANTAGE OF THE INVENTION According to this invention, the skin shape model which considered the shape of texture and three-dimensional shapes, such as a face and a hand, can be produced | generated.

It is a figure which shows an example of a function structure of a skin shape model production | generation apparatus. It is a figure which shows an example of the hardware constitutions which can implement | achieve the skin shape model production | generation process in this embodiment. It is a flowchart which shows an example of the skin shape model production | generation process procedure in this embodiment. It is a figure for demonstrating the process which produces | generates the vertex which comprises a polygon. It is a figure for demonstrating the process which produces | generates a vertex on the inside of a pore, a skin groove, and a cuticle. It is a figure which shows an example of the parameter which changes each shape of a pore, a skin groove, and a skin mound. It is a figure which shows an example of the skin fragment image produced | generated by this embodiment mentioned above. It is a figure for demonstrating the mapping method to the face shape using a texture shape. It is a figure which shows the example of a display screen at the time of 3D face shape model production | generation. It is a figure which shows an example of the shape of the fragment image corresponding to the partial area | region of a face. It is a figure for demonstrating the specific example of the mapping process to the fine shape of skin. It is a figure for demonstrating the case where a coordinate value is calculated. It is a figure for implement | achieving the weight reduction method of data. It is a figure for demonstrating the 1st application example to which this embodiment is applied. It is a figure which shows the correspondence of a target shape and a three-dimensional face shape model. It is a figure for demonstrating the 2nd application example to which this embodiment is applied.

<About the present invention>
The present invention uses a skin shape modeling technique that can simultaneously control micro shapes such as pores, skin ridges, skin grooves, etc., and contour shapes such as faces and hands, such as round shapes and square shapes, to any shape at the same time. Generate polygon data with high expressive skin shape.

  Specifically, the texture shape model can be reproduced not only in a square area but also in an irregular area such as a triangle or a round shape. Further, the generated textured polygon data of the skin is mapped to the polygonal data of a three-dimensional shape of an object such as a face or a hand, and at that time, it can be further deformed in accordance with a change in the curvature of the shape.

  Here, for example, when the three-dimensional shape is a human face, the texture shape differs depending on the part of the face. Therefore, in the present invention, for example, based on a predetermined condition such as a tendency of a change in texture shape, the face area is divided into about 10 to 20, and after changing the texture shape for each divided part, the face area is mapped to each area. .

  Furthermore, in the present invention, for example, three-dimensional morphing or the like is applied to the deformation of the face shape polygon data, thereby enabling an arbitrary contour shape change. Specifically, the shape or the like presented on the feature map or the like as a reference for change is set as a target shape, and the shape can be transformed into an arbitrary contour shape while numerically measuring the influence of the shape. Further, a simple deformation process can be realized without directly adjusting data by the deformation method of the present invention.

  Hereinafter, embodiments in which the skin shape model generation device, the skin shape model generation method, and the skin shape model generation program according to the present invention having the above-described features are suitably implemented will be described in detail with reference to the drawings. In the following description, a human face shape is used as an example of a skin shape model. However, the present invention is not limited to this, and may be other partial shapes such as hands and feet. It may be the whole body.

<Skin shape model generation device: functional configuration example>
A functional configuration of the skin shape model generation apparatus according to the present embodiment will be described with reference to the drawings. FIG. 1 is a diagram illustrating an example of a functional configuration of a skin shape model generation apparatus.

  A skin shape model generation apparatus 10 shown in FIG. 1 includes an input unit 11, an output unit 12, a storage unit 13, a pore generation unit 14, a region division unit 15, a cuticle skin groove determination unit 16, and a polygon generation. Means 17, texture shape modeling means 18, face shape modeling means (skin shape modeling means) 19, image generation means 20, transmission / reception means 21, and control means 22.

  The input unit 11 accepts inputs such as start / end and setting of various instructions related to the skin shape model generation process according to the present embodiment from, for example, a user who uses the skin shape model generation device 10. Note that the input unit 11 includes a pointing device such as a keyboard or a mouse if it is a general-purpose computer such as a PC (Personal Computer). Further, the input unit 11 may be a voice input device such as a microphone capable of the above-described input by voice or the like.

  The output unit 12 outputs the content input by the input unit 11 and the content executed based on the input content. The output means 12 is composed of, for example, a display or a speaker. The output unit 12 may include a printing device such as a printer. Note that the input unit 11 and the output unit 12 described above may have an input / output integrated configuration such as a touch panel, for example, when the skin shape model generation device 10 is a smartphone, a tablet terminal, or the like.

  The storage unit 13 stores various information necessary in the present embodiment. Specifically, various programs for executing the skin shape model generation processing in the present embodiment, various setting information, and the like are stored. For example, the storage means 13 records the parameters for changing the shape of the pores, the shape of the skin, the shape of the skin groove, the flow and the like. For example, the storage means 13 includes a radius representing the shape of the pore, a depth, an opening shape, an interval for determining the arrangement of the pores, a parameter such as messiness, a parameter representing the shape of the skin, a parameter such as a messiness, And parameters such as depth, width, and messiness representing the shape of the skin groove.

  More specifically, the storage means 13 uses the texture shape modeling means 18 as parameters for modeling the texture shape, for example, with respect to the pores. For example, the average interval between the pores, the average radius of the pores, the average depth of the pores, the pores Parameters such as the randomness of the radius, the randomness of the pore position, and the randomness of the pore depth are stored. Further, the storage means 13 stores parameters such as the direction dependency of the depth of the groove, the maximum value of the depth of the groove, the randomness of the depth of the groove, and the like. Moreover, the memory | storage means 13 memorize | stores parameters, such as the maximum value of a skin height, the randomness of a skin height, etc. regarding a skin. In addition, the storage unit 13 stores parameters such as a polygon size (for example, a guideline for the length of one side of a triangular polygon). In addition, the storage unit 13 stores parameters for performing face shape modeling (for example, skin fragment deformation data and parameters for curvature deformation) in the face shape modeling unit 19.

  The storage unit 13 can set the above-described parameters according to various skin conditions. In addition, the storage unit 13 can write or read the above-described various information at a predetermined timing as necessary. Here, the storage means 13 is a collection of various kinds of information as described above, and a database structured systematically so that such information can be searched and extracted using, for example, keywords. It may also have a function as Further, the information stored in the storage unit 13 may be acquired from an external device via a communication network, for example.

  The pore generation means 14 generates a plurality of pores arranged with a predetermined distribution in a preset skin region. For example, when pores are generated by arranging pores in a grid pattern in the skin region, for example, the pore generation means 14 adds random numbers to the center coordinate value of each generated pore, thereby making the pore arrangement random. It can also be added.

  The pore generation means 14 can also add randomness by adding a predetermined random number to the radius, depth, etc. of the generated pore. It should be noted that parameters such as a predetermined random number value to be added to the radius, depth, and arrangement of the pores used when adjusting the pore shape by the pore generation means 14 are preliminarily set to the skin state, the predetermined pore shape, etc. Accordingly, it is stored in the storage means 13 or the like.

  The region dividing unit 15 divides the skin region by connecting the center points of adjacent pores among the plurality of pores generated by the pore generating unit 14. The area dividing means 15 divides the skin area by a triangular area obtained by connecting three adjacent pores among a plurality of pores using, for example, the Delaunay triangular mesh algorithm. In the present embodiment, the shape is not limited to a triangle, and may be divided into, for example, a quadrangle or the like in order to represent a variety of skin conditions.

  Here, for example, the triangles of the skin region formed by the division by the region dividing unit 15 have the sides as skin grooves and the triangles surrounded by the sides as the skins. Moreover, a skin groove is formed by the line segment which connects between pores.

  The cuticle skin groove determining means 16 specifically determines the shapes of the skin and the skin groove obtained by the area dividing means 15. The cuticle skin groove determining means 16 sets, for example, the height of the skin layer with a predetermined random number, and sets the width of the skin groove and the depth of the skin groove with a predetermined random number. It should be noted that a predetermined random number value to be added to the height of the skin, the width of the skin, the depth of the skin, and the depth of the skin used when adjusting the shape of the skin, the skin groove by the skin skin groove determining means 16. Are stored in advance in the storage means 13 or the like in accordance with the skin condition, the predetermined skin groove, the shape of the skin, etc.

  The polygon generation unit 17 divides the pores generated by the pore generation unit 14 and the shapes of the skin and the skin groove determined by the skin mound skin groove determination unit 16 into polygons which are finer triangle groups. For example, the polygon generation unit 17 generates vertices at the center position inside the pores generated by the pore generation unit 14, and generates vertices at predetermined intervals on the outer periphery of the pores. Further, the polygon generation unit 14 may generate concentric circles on the inner side of the outer periphery of the pores based on the depth and radius of the pores, and generate vertices on the concentric circles at predetermined intervals.

  In addition, for example, the polygon generation unit 17 generates vertices at predetermined intervals on the skin groove determined by the duck skin groove determination unit 16. Here, the polygon generation means 17 is good to generate | occur | produce a vertex on a skin groove at predetermined intervals from the outer periphery of a pore.

  In addition, for example, the polygon generating unit 17 generates vertices at predetermined intervals in the hides determined by the cuticle skin groove determining unit 16. Here, the polygon generation means 17 generates vertices in the skin at predetermined intervals from the outer periphery of the pores and the skin groove, for example, when the vertex is generated at a portion where the center of gravity of the triangle of the skin is highest. Good.

  The polygon generation means 17 connects the vertices of the pores generated as described above, the vertices on the skin groove, the vertices on the skin hill using the Delaunay triangular mesh algorithm or the like, and the pores, skin grooves, Divide the shape of the hill into finer triangles (polygons). Further, the polygon generating means 17 generates a three-dimensional face shape polygon for generating a skin shape model.

  The texture shape modeling means 18 models the texture shape of a skin fragment in a predetermined area (for example, a square area) based on various parameters such as pores, skin hills, and skin grooves related to texture. Further, the texture shape modeling means 18 can generate a texture-shaped skin fragment by changing parameters in accordance with, for example, the position of mapping (pasting) to a three-dimensional face shape polygon. In the present embodiment, a fine texture shape can be expressed by the processing of the texture shape modeling means 18.

  The face shape modeling means 19 performs modeling into a three-dimensional three-dimensional face shape based on a face type (for example, contour shape) parameter. Specifically, the texture shape modeling result of the skin fragment obtained by the texture shape modeling means 18 is mapped (pasted) to a predetermined position of the three-dimensional face shape polygon. At this time, the face shape modeling means 19 can be deformed into a predetermined shape or three-dimensionally deformed with a predetermined curvature in accordance with the face part to which the skin fragment is mapped. Note that the face shape modeling means 19 can change to an arbitrary contour shape by applying a three-dimensional morphing method in the case of deformation of face shape polygon data. In the present embodiment, a macro face shape can be expressed by the processing of the face shape modeling means 19.

  In this embodiment, the image generation unit 20 generates various images to be provided to the user. For example, the image generation unit 20 generates an image that displays parameters for performing texture shape modeling, parameters for performing face shape modeling, and the like for the polygon shape obtained by the polygon generation unit 17, or Each of the parameters is operated to generate a fragment image and a three-dimensional face shape model (three-dimensional skin shape model) image while deforming. In this embodiment, when mapping the skin texture polygon data to the face shape polygon data, a predetermined modeling image may be generated by three-dimensionally deforming in accordance with the curvature change of the face shape. it can.

  Note that the shape of a person's texture differs depending on the part of the face. Therefore, in the present embodiment, for example, the face area is divided based on a predetermined condition such as a tendency of change in texture shape or an area where muscle composition is anatomically different, and the texture shape is divided for each divided part. And then map to each region. The number of divisions of the face area is preferably about 10 to 20, for example, but is not limited to this. Thereby, in this invention, the deformation | transformation suitable for a texture shape can be performed and modeling suitable for each face shape can be performed.

  As the predetermined condition, for example, the face area can be divided based on the evaluation result by the skin evaluation method shown in Japanese Patent Application Laid-Open No. 2011-212308 filed by the present application. It is not limited.

  Moreover, in this invention, the skin shape image which consists of various skin states, such as healthy skin, pore skin, dry skin, etc. is produced | generated by changing the parameter mentioned above, and a face shape model image is produced using the produced | generated skin image. Can be generated. Thereby, a quantitative shape simulation can be realized. In the present embodiment, the above-mentioned healthy skin is, for example, “healthy skin having a uniform texture with little variation in texture”, and pore skin is, for example, “skin with large pores and noticeable”, and is dry The skin can be, for example, “uneven dry skin with few textured irregularities”, but is not limited to this in the present invention, and other skin states may be used.

  The image generation unit 20 outputs the generated image to the screen of the output unit 12 and the like, presents it to the user, etc., stores it in the storage unit 13, or transmits it to an external device via the transmission / reception unit 21. be able to.

  The transmission / reception means 21 transmits / receives information necessary for each process in the present embodiment, an execution program for realizing the skin shape model generation process in the present invention, and the like from an external device that can be connected using, for example, a communication network. Is an interface that can. Therefore, the transmission / reception means 21 can acquire the latest parameter information etc. from an external device etc., for example, and can transmit the various information produced | generated by the skin shape model production | generation apparatus 10 to an external device etc.

  The control means 22 controls the entire configuration of the skin shape model generation apparatus 10. For example, the control means 22 controls at least one of pore generation, region division, cuticle skin groove determination, polygon generation, texture shape modeling, face shape modeling, image generation processing, and the like.

<Skin shape model generation device 10: hardware configuration example>
Here, the execution program (skin shape model generation program) for causing the computer to execute each function of the above-described skin shape model generation apparatus 10 is generated, and installed in, for example, a general-purpose PC, server, etc. Shape model generation processing or the like can be realized. FIG. 2 is a diagram illustrating an example of a hardware configuration capable of realizing the skin shape model generation process in the present embodiment.

  2 includes an input device 31, an output device 32, a drive device 33, an auxiliary storage device 34, a memory device 35, a CPU (Central Processing Unit) 36 for performing various controls, and a network connection device 37. Are connected to each other via a system bus B.

  The input device 31 includes, for example, a keyboard and a pointing device such as a mouse operated by a user, a voice input device such as a microphone, and the like, and inputs various operation signals such as execution of a program from the user.

  The output device 32 has a display for displaying various windows, data, and the like necessary for operating the computer main body that performs processing in the present embodiment, and displays the execution progress and results of the control program executed by the CPU 36.

  Here, the execution program installed in the computer main body in the present invention is provided by, for example, a portable recording medium 38 such as a USB (Universal Serial Bus) memory or a CD-ROM. The recording medium 38 can be set in the drive device 33, and an execution program included in the recording medium 38 is installed from the recording medium 38 to the auxiliary storage device 34 via the drive device 33.

  The auxiliary storage device 34 is a storage means such as a hard disk, and stores an execution program according to the present invention, a control program provided in a computer, etc., and performs input / output as necessary.

  The memory device 35 stores an execution program read from the auxiliary storage device 34 by the CPU 36. The memory device 35 includes a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. Note that the auxiliary storage device 34 and the memory device 35 described above may be configured integrally as a single storage device.

  The CPU 36 controls processing of the entire computer, such as various operations and input / output of data with each hardware component, based on a control program such as an OS (Operating System) and an execution program stored in the memory device 35. By doing so, each processing in face shape modeling is realized. Various information necessary during the execution of the program may be acquired from the auxiliary storage device 34 and the execution result or the like may be stored.

  The network connection device 37 acquires an execution program from an external device connected to the communication network or executes the program by connecting to a communication network such as the Internet or a LAN (Local Area Network). The execution result obtained in this way or the execution program itself in this embodiment is provided to an external device or the like.

  With the hardware configuration described above, it is possible to execute the skin shape model generation process in the present invention. Further, by installing the execution program, the skin shape model generation process in the present embodiment can be easily realized by a general-purpose personal computer or the like.

<Skin shape model generation processing procedure>
Next, the skin shape model generation processing procedure in the present embodiment will be described using a flowchart. FIG. 3 is a flowchart showing an example of a skin shape model generation processing procedure in the present embodiment.

  In the example of FIG. 3, the skin shape model generation processing generates, for example, grid-like pores in a preset skin region (S01), and connects the center points of the generated pores, for example, to divide the skin region (S02). Next, in the skin shape model generation process, the shapes of the skins and skin grooves formed by dividing the skin region in the process of S01 are determined (S03). Here, pores, skins, and skin grooves are formed by performing the processes of S01 to S03 in order.

  Next, in the skin shape model generation process, in order to three-dimensionally represent each shape of the pores, skins, and skin grooves formed by the processes of S01 to S03, triangular polygons to be further divided into fine triangle groups (polygons) are represented. Generate (S14). Next, in the skin shape model generation process, the texture shape is modeled using the parameters determined for forming a predetermined skin image by the processes from S01 to S04 (S05), and then the process of S04. The face shape is modeled using the obtained texture shape (S06). When face shape modeling is performed, before the modeling, the polygon is made indefinite based on each part of the face, and the curvature is added to model the face shape.

  Thereafter, the skin shape model generation process generates a skin image representing a predetermined skin state such as healthy skin, pore skin, dry skin, etc., and generates a face shape model image using the generated skin image (skin fragment). The generated skin image, face shape model image, and the like are displayed and output on the screen (S07).

  At this time, for example, while viewing the skin image displayed on the screen, the user changes the part or all of the parameters to display the skin image with respect to the above-described pore generation, skin mound / skin determination, A desired skin image can be acquired. Further, the face shape model can be acquired by applying the above-described skin image to a predetermined part of the face shape.

  In the skin shape model generation process, various parameters corresponding to the skin image obtained by the process of S07 are stored in the storage unit or the like (S08). In the process of S08, an image may be stored together with the parameters. Thereby, in the skin shape model generation process, when generating a skin image from the next time, the parameters stored in the storage means and the parameters corresponding to the target skin image are selected, and the skin image or A face shape model or the like can be displayed. Further, in the present embodiment, by performing the above-described processing a plurality of times, by analyzing a plurality of parameters stored in the storage means 13, analysis of each skin state such as healthy skin, pore skin, dry skin, etc. It can also be used for evaluation relating to texture. Therefore, a quantitative shape simulation can be realized by the skin shape model generation process in the present embodiment.

<About processing of S01 to S03>
Here, the process of S01-S03 mentioned above is demonstrated concretely. For the processing of S01 to S03 (pattern generation processing), for example, a method shown in Japanese Patent Application Laid-Open No. 2011-161105 filed by the present applicant can be used.

  Specifically, in the present embodiment, the pore generation process (S01) generates pores arranged in a predetermined distribution (for example, a lattice shape) in a predetermined skin region, and the adjacent pores are linearly formed. A pore can be generated by a pattern constituting a set of triangles obtained by tying. The pore generation processing adds randomness by adding a predetermined random number to the radius, depth, and position (arrangement) of the generated pores. For example, the pore generation process can add randomness to the arrangement of pores by adding a predetermined random number to the center coordinate value of each generated pore. In addition, for a specific example of a predetermined random number value that the pore generation process adds to the radius, depth, and arrangement of the pores, for example, the technique described in Japanese Patent Application Laid-Open No. 2011-161105 described above may be used. Yes, but not limited to this.

  Next, the region division processing (S02) generates a pattern for connecting the center points of the pores generated by the pore generation processing using a straight line between adjacent pores, using, for example, the Delaunay triangular mesh algorithm. Thus, the skin region is divided into a set of triangles. Here, in the triangle of the formed skin region, each side is a skin groove, and each triangle surrounded by each side is a skin hill. The skin groove is formed by a line segment connecting pores.

  Next, the cuticle skin groove determination process (S03) determines the shape of the formed cuticle and skin groove. For example, the hide depth determination means sets the height of the cuticle with a predetermined random number, and sets the width and depth of the cuticle with a predetermined random number. Note that specific examples of the predetermined random number value added to the height of the skin, the width of the skin, and the depth of the skin by the skin mound determining means are described in, for example, the above-mentioned JP-A-2011-2011. The method described in Japanese Patent No. 161105 can be used, but is not limited thereto.

<Parameters for changing skin condition in textured shape>
Here, parameters for changing the skin state in the texture shape will be described. For example, for skin conditions such as healthy skin, pore skin, and dry skin, a predetermined skin condition is generated by setting parameters such as “average radius of pores” and “maximum value of skin height”. .

  For example, for healthy skin, “average radius of pores” is set to “0.05”, “maximum value of skin height” is set to “0.05”, and for skin with pores, for example, “pores” “Average radius of” is set to “0.1”, “maximum value of skin height” is set to “0.05”, and for dry skin, for example, “average radius of pores” is set to “0.05”, “ “Maximum value of hide height” can be set to “0.01”, but is not limited thereto.

  As described above, in the present embodiment, by setting parameters such as “average radius of pores” and “maximum value of skin height” in accordance with the skin state, the image generating means 20 performs predetermined skin. The state can be expressed. In addition to the parameters described above, for example, parameters used by the pore generation means 14 (for example, average pore spacing, pore position irregularity, pore radius irregularity, etc.), and skin mound skin groove determination means are used. Parameters (for example, the roughness of the hill height, the maximum value of the groove depth, the roughness of the groove depth, the width of the groove, etc.) can be set as adjustable parameters.

  Accordingly, in the present embodiment, for example, by the pore generation unit 14, for example, “average pore interval” is “0.5”, “randomness of pore positions” is “0.3”, and “randomness of pore radius”. By adjusting the parameters such as “0.1”, the arrangement of pores and the shape of the pores can be changed.

  Similarly, in the present embodiment, for example, the “skin height irregularity” is set to “0.05”, the “maximum value of the skin depth” is set to “0.01”, By adjusting the parameters such that “messiness of skin depth” is “0”, “width of skin groove” is “0.1”, etc., the shape of the skin and skin groove can be changed.

  The unit of each parameter described above is, for example, millimeter. In particular, in the “messiness of the hide hill height” and the “messiness of the skin depth”, when “randomness is a”, the average value of each parameter is randomized within a range of a millimeter. Means that the value changes, so the unit is millimeters.

  As described above, according to this embodiment, by setting parameters that change the shape of the pores, skins, and skins that form the skin shape, the arrangement, shape, skins, and skins of the pores can be changed. It is possible to change and express various skin conditions. Note that the types and values of the parameters described above are not limited to this in the present invention, and a plurality of parameters may be combined and applied as new parameters.

<Polygon generation processing>
Next, the polygon generation process described above will be described. FIG. 4 is a diagram for explaining processing for generating vertices constituting a polygon. As shown in FIG. 4, the polygon generation process divides the pattern generated by the processes of S01 to S03 into finer triangle groups (polygons), so that each shape of pores, skins, and skin grooves is three-dimensional. To express.

  First, the polygon generation processing, for example, for a pore, for example, generates a vertex at the center position of the pore, generates a concentric circle within the pore from the depth and radius of the pore, and creates a predetermined interval between the generated concentric layers. Generate vertices. Further, the polygon generation processing generates vertices with respect to the hides, for example, so that the center of gravity of the triangle is the highest in the hides. Further, the polygon generation processing generates vertices at predetermined intervals along the depth on the skin groove, for example.

  Next, the polygon generation process connects the vertices generated on the pores, skins, and skin grooves using, for example, the Delaunay triangular mesh algorithm, thereby further reducing the pore, skin, and skin groove patterns into a more detailed triangle group (polygon). Divide and generate polygons.

<Process for generating vertices in pores, on top of skin grooves, and in skins>
Here, the generation process of the above-mentioned pores, skin grooves, and vertices of the skin is described in more detail. FIG. 5 is a diagram for explaining a process of generating vertices on the pores, the skin groove, and the inside of the skin. In the polygon generation process, vertices are generated on the pores, on the skin grooves, and inside the hills, and the last generated vertices are connected. In addition, the process which produces | generates a vertex in a pore, a skin groove, and the inside of a skin may be performed from any process.

  As shown in FIG. 5A, in the polygon generation processing, first, a vertex indicated by an arrow A is generated at the center position of the pore, and then the vertex is generated at a predetermined interval on the outer periphery of the pore. Here, when the pore is larger than the resolution of the triangular polygon, for example, the “average radius of the pore” given by the user is compared with the “value of the length of one side of the triangular polygon” given by the user. If it exceeds 1.0 times, a concentric circle is generated inside the outer periphery of the pore based on the depth and radius of the pore as described above.

  For example, if the pore radius is r and the length of one side of the triangular polygon is e, the number of pore radius divisions is n = [r / e] +1 (where [x] is the decimal point of x The following are rounded down integers), and concentric circles having a radius ir / n are generated (where i is an integer from 1 to (n-1)).

  Next, in the polygon generation process, vertices are generated at predetermined intervals on concentric circles generated inside the outer periphery of the pores. This creates a layer inside the pores.

  In the polygon generation process, vertices are created at predetermined intervals along the depth on the skin groove. For example, when the maximum depth of the crevice is dmax and the randomness of the crevice depth is drando, the value obtained by subtracting the random number generated during the interval [0, dradom] from dmax is the depth. The polygon generation means may generate vertices on the skin groove at a predetermined interval from the outer periphery of the pore as indicated by an arrow B in FIG.

  In the polygon generation process, vertices are created at regular intervals within the hide. Here, the polygon generating means generates vertices in the skin at a predetermined interval from the outer periphery of the pores and the skin groove as indicated by an arrow C in FIG. 5 (A), and as described above, A vertex is generated at a portion where the center of gravity of the triangle is highest.

<Triangular polygon generation result>
Further, in the example of the triangular polygon generation result shown in FIG. 5B, the polygon generation processing is performed by using the Delaunay triangular mesh algorithm or the like for the vertexes of the pores, the vertices on the skin groove, and the vertices on the skin hill generated in the step S04. The shape of pores, skin grooves, and skin mounds is divided into finer triangles (polygons) on the skin region. Thereby, each shape of a pore, a skin mound, and a skin groove can be expressed in three dimensions.

<Examples of parameters that change the shape of pores, skin grooves, and dunes>
Here, an example of parameters for changing the shapes of pores, skin grooves, and skin mounds will be described. FIG. 6 is a diagram illustrating an example of parameters for changing the shapes of pores, skin grooves, and skin hills. In this embodiment, for example, as shown in FIG. 6 (A), as a parameter for changing the shape of the pore, for example, a parameter for changing the shape of the concave portion of the pore into a round shape or a shape in which the parabola is inverted is set. Keep it. Further, in this embodiment, as shown in FIG. 6B, the shape of the opening of the pore is not limited to a circle, but is a shape that extends in one direction (for example, a major axis and a minor axis such as an elliptical shape). Set the parameter to be changed to a circle.

  Further, in the present embodiment, as shown in FIG. 6C, as a parameter for expressing the randomness with respect to the width of the skin groove, for example, the width of the skin groove is changed in a stepwise manner such as a thin width or a thick width. A plurality of width flute parameters for changing the thickness of the are set in advance. In the present embodiment, as shown in FIG. 6D, as a parameter for changing the flow of the skin groove, for example, a parameter for changing the flow of the skin groove as if stretched in the left and right directions is set. . In this way, by setting a parameter for changing the flow of the skin groove, for example, it is possible to represent the flow of the cheek muscles from the nose to the lower cheek.

  Further, in the present embodiment, as shown in FIG. 6E, as a parameter for changing the shape of the skin, for example, a parameter for changing the shape of the swelling of the skin to various mountain shapes, trapezoids, or the like is used. Set it. In the present embodiment, as shown in FIG. 6F, parameters for adding fine irregularities to the internal shape of the skin are set.

  As described above, various skin states can be generated by setting parameters that change the shapes of pores, skin grooves, and skin hills that form the skin shape. Thereby, for example, it is also possible to represent the skin state at a predetermined part of the face. In addition, the polygon generation processing can generate, for example, a skin shape polygon for a three-dimensional face in addition to the above-described polygon related to the texture shape by applying the above-described processing.

<Example of Screen Generated by Screen Generation Unit 20>
Next, an example of a screen generated by the screen generation unit 20 will be described with reference to the drawings. FIG. 7 is a diagram illustrating an example of a skin fragment image generated according to the above-described embodiment. 7A to 7C show an example of a skin fragment image generated by the texture shape modeling means 18 described above. 7A shows a fragment image 40-1 of healthy skin (prepared skin), and FIG. 7B shows a fragment image 40-2 of pore skin (skin with conspicuous pores). 7 (C) shows a fragment image 40-3 of dry skin. These images can be generated by changing the parameters described above.

  In the healthy skin fragment image 40-1 shown in FIG. 7A, the skin groove is continuous, the skin is full and the shape is uniform. At this time, as parameters, for example, in the diagram of FIG. 7A, “number of pores” is set to “460”, “number of hides” is set to “888”, and “number of skin grooves” is set to “1347”. The “number of polygon vertices” is generated as “76491” and the “number of polygons” is generated as “152908”. However, the present invention is not limited to this.

  Further, the pore skin fragment image 40-2 shown in FIG. 7B is an image having a wide and deep pore. At this time, as parameters, for example, in the diagram of FIG. 7B, “number of pores” is set to “468”, “number of hides” is set to “908”, and “number of skin grooves” is set to “1375”. The “number of polygon vertices” is generated as “81672” and the “number of polygons” is generated as “163284”. However, the present invention is not limited to this.

  In addition, the dry skin fragment image 40-3 shown in FIG. 7C has a shallow skin groove and a flat skin. At this time, as parameters, for example, in the diagram of FIG. 7C, “the number of pores” is set to “464”, “the number of hides” is set to “898”, and “the number of skin grooves” is set to “1361”. The “number of polygon vertices” is generated as “77351” and the “number of polygons” is generated as “154613”. However, the present invention is not limited to this. Thus, in this embodiment, it is possible to generate any skin fragment image that meets the purpose by changing the parameters.

<Face shape model generation in the face shape modeling means 19>
Next, an example of face shape model generation in the face shape modeling means 19 will be described. In the present embodiment, face shape modeling is performed by mapping (pasting) to a preset face three-dimensional shape using the texture shape modeling result (skin fragment) described above.

  Here, the skin quality of the face varies depending on the part of the face. Specifically, for example, pores are conspicuous on both sides of the nose, and the forehead has a texture flowing sideways. Therefore, in the present embodiment, the face area is divided into a plurality of parts in consideration of the difference in skin quality, a texture shape image (skin fragment image) is generated for each divided face area, and the skin fragment shape is further deformed. 3D face shape modeling by changing the curvature. Here, FIG. 8 is a diagram for explaining a mapping method to the face shape using the texture shape.

  Here, in the present embodiment, the face area shown in FIG. 8A is, for example, “(1) an area from the forehead to the temple”, “(2) an area including the nose”, “(3) an area around the eye” "Area", "(4) Side area", "(5) Area including nose from nose tip", "(6) Area including cheek", "(7) Area including above lips", "(8) Lips" Are divided into nine regions, “region including” and “(9) region including chin”. In addition, about the area | region with right and left symmetry in a face area, the process which divides the symmetrical side similarly is performed. In the above-described division, for example, face division can be performed for each tendency of texture shape change or for each region having an anatomically different muscle composition, but the region to be divided is not limited thereto.

  In the face shape model generation method according to this embodiment, first, the texture shape modeling means 18 creates a skin fragment image for each of the above-described divided portions. Therefore, in this embodiment, the parameter which considered the skin quality is set and the skin fragment image mentioned above is acquired.

  In the example of FIG. 8, in order to reproduce the characteristics of the divided area of “(6) area including cheeks” (FIG. 8B) among the divided areas of the face shown in FIG. Using a parameter corresponding to the set divided area, a textured skin fragment image 41 of the area including the cheek is generated (FIG. 8C). In the present embodiment, the skin fragment image of FIG. 8C is mapped to a preset three-dimensional face-shaped polygon 42 (FIG. 8D). In the present embodiment, the face shape is modeled using the skin fragment image while reproducing a texture shape that is different for each part obtained by dividing the above-described processing.

  The mapped image is generated by the image generation means 20 and displayed on the screen. At this time, in the present embodiment, the image can be enlarged / reduced or rotated. FIG. 9 is a diagram illustrating an example of a display screen when generating a three-dimensional face shape model. In the present embodiment, at least one of enlargement, reduction, and rotation in a predetermined direction can be performed on an image of a three-dimensional face shape model (three-dimensional skin shape model) displayed on a screen or the like. . For example, in the present embodiment, as shown in FIG. 9A, a state in which the target skin fragment image 41 is mapped for each partial region of the face of the three-dimensional face-shaped polygon 42 is presented to the user in an enlarged display. can do. In the present embodiment, as shown in FIG. 9B, the user can rotate the three-dimensional face-shaped polygon 42 in a predetermined three-dimensional (x, y, z) direction so that the user can The content of mapping the skin fragment image 41 on the polygon 42 can be confirmed accurately.

  Here, FIG. 10 is a diagram illustrating an example of the shape of the fragment image corresponding to the partial region of the face. In the present embodiment, as shown in FIG. 10, the skin fragment shapes 41-1 to 41-4 are deformed corresponding to the partial areas of the face. Further, in the present embodiment, for each deformed skin fragment shape 41, appropriate mapping is realized by changing the curvature corresponding to the curve of the face surface corresponding to the partial region.

<Specific example of skin shape mapping process>
Here, in the face shape modeling described above, for example, a specific example (algorithm example) of mapping processing of a fine skin shape will be described with reference to the drawings. FIG. 11 is a diagram for explaining a specific example of the mapping process to the fine shape of the skin. FIG. 12 is a diagram for explaining a case where coordinate values are calculated.

  In FIG. 11A, as the data structure of the face shape model (three-dimensional face shape polygon 42), the coordinate values (x, y, z) and the shape in the real coordinate system are expressed for each vertex constituting the face shape. It has coordinate values (u, v) when expanded two-dimensionally. In FIG. 11B, coordinate values (p, q, r) in a coordinate system in which a local part of the face shape is approximated by the XY plane are set for each vertex constituting the fine skin shape.

  As a processing procedure, first, the ratio of the length of the actual coordinate system of the face shape and the coordinate system at the time of development is calculated. For example, in this embodiment, when both end points of the ridge line on the face shape are a1 and a2, the distance d1 between a1 and a2 in the real coordinate system and the distance d2 between a1 and a2 in the unfolded coordinate system. And the average value e of the ratio of d2 to d1 is obtained.

Next, in the present embodiment, the fine skin shape is reduced by multiplying the coordinate value (p, q, r) of the fine skin shape by the average value e, and (p ′, q ′, r ′) is added. Move in parallel. Moreover, in this embodiment, the following (a)-(e) is implemented about each vertex (p ', q', r ') which comprises skin fine shape.
(A) When the coordinate values of the three vertices of each triangular area constituting the face shape are a1 (u1, v1), a2 (u2, v2), a3 (u3, v3), the point b (p ′, A triangular region including q ′) is specified in the development coordinate system.
(A) The areas s1 to s3 of the three triangles formed when the point b and the points a1, a2, and a3 are connected by line segments are represented by s1 = the area of the triangle b.a2 and a3, and s2 = the triangle b.a3. The area of a1, s3 = the area of triangle b.a1.s2.
(C) When the coordinate values of a1, a2, a3 in the real coordinate system are a1 (x1, y1, z1), a2 (x2, y2, z2), a3 (x3, y3, z3), the point b The coordinate values (x ′, y ′, z ′) in the real coordinate system are obtained as follows.
x '= s1 * x1 + s2 * x2 + s3 * x3
y ′ = s1 · y1 + s2 · y2 + s3 · y3
z ′ = s1 · z1 + s2 · z2 + s3 · z3
However, at this time, the fine skin shape is affixed to the face shape as a flat surface.
(D) The normal vectors (x ″, y ″, z ″) of the point b are calculated by interpolating the normal vectors of a1, a2, a3 with the same equation as (c) above.
(E) By attaching irregularities to the skin fine shape according to the following formula, the application of the skin fine shape to the face shape is completed.
x ′ = x ′ + r ′ · x ″
y ′ = y ′ + r ′ · y ″
z ′ = z ′ + r ′ · z ″
In this embodiment, as shown in FIG. 12, the coordinate values (x ′, y ′, z ′) on the plane of the point b are interpolated by the coordinate values of the real coordinate system of the points a1, a2, a3. Then, by adding the coordinate value in the direction of the normal vector (x ″, y ″, z ″) at the point b, it is possible to calculate the coordinate value of the point b taking into account the unevenness. . The above-described processing is performed by, for example, the above-described face shape modeling unit 19 or the like, but is not limited thereto.

<Global deformation of face shape>
Here, in the present embodiment described above, as the face shape, a shape is set in advance such as an elliptical sphere or a rectangular parallelepiped, and the coordinate values in the real coordinate system of each vertex constituting the face shape are set to (x, y, z), and the center point of the face shape in the real coordinate system is (a, b, c), the face shape is obtained by executing the following processes (a) and (b) for each vertex. The global deformation of is possible.
(A) A half line extending in the direction of (x, y, z) from (a, b, c) is generated, and an intersection (x ′, y′.z ′) between this and an elliptic sphere or a rectangular parallelepiped is obtained.
(A) By using the following equation, the vertex is moved from (x, y, z) to (x ″, y ″, z ″) by interpolation with an elliptical sphere or a rectangular parallelepiped, x ″ = sx + (1− s) x '
y ″ = sy + (1−s) · y ′
z ″ = sz + (1−s) · z ′
The above-described processing is performed by, for example, the above-described face shape modeling unit 19 or the like, but is not limited thereto.

<About weight reduction of data>
Here, in the present embodiment, by performing the above-described skin shape model generation process, a highly accurate three-dimensional skin shape model corresponding to each divided region of the face can be acquired. May increase the number of polygons generated, which may affect the processing time. Therefore, in the present embodiment, in order to reduce the weight of the data, the weight of the data is reduced by reducing the number of polygons when a predetermined condition is satisfied.

  FIG. 13 is a diagram for realizing a data weight reduction technique. In the example of FIG. 13A, paying attention to the fact that the shape of the skin mound has fewer features than the pores and skin grooves, the number of polygons is reduced by roughening only the polygon of the skin mound. Thus, for example, before polygon reduction processing (BEFORE) shown in FIG. 13A, pores (Pore): 0.04, furrow (Furrow): 0.04, and ridge (Ridge): 0.04. In the parameter condition, the number of polygons was 88666, while the polygon number of 41029 was roughened by coarsening only the polygons of the hill with Pore: 0.04, Furrow: 0.04, Ridge: 0.08. (AFTER).

  That is, in the present embodiment, as shown in FIG. 13B, when the fragment image is generated, for example, when the sizes of the pores, skin grooves, and polygons of the skin are set separately, the pores, The number of polygons after processing is reduced by performing the process of roughing only polygons of the hill with relatively few features compared to the skin groove. In the present embodiment, not only the skins but also the pores and the skin grooves may be roughened. In this case, it is preferable that the ratio of the skins to be roughened is larger than the ratio to the pores and skin grooves.

  The weight reduction of the data by the polygon reduction described above may be performed, for example, by an instruction from the user, and the face shape model to be generated is set in advance by setting the number of polygons, the data amount, and the like as threshold values. When the set number of polygons or data amount threshold is exceeded, the above-described weight reduction processing may be performed. Note that the above-described weight reduction processing can be realized by, for example, the polygon generation unit 17 performing the determination by the face shape modeling unit 19 and then performing the texture shape modeling processing, the face shape modeling processing, and the like again, but is not limited thereto. It is not something.

<Application example>
Next, an application example to which this embodiment is applied will be described. FIG. 14 is a diagram for explaining a first application example to which the present embodiment is applied. The example of FIG. 14 shows a screen example of face shape simulation utilizing the above-described 3D face shape morphing.

  For example, in the software (program) for realizing the skin shape model generation process in the present embodiment, for example, a three-dimensional face shape model is converted into a first shape (for example, an ellipse) set in advance as shown in FIG. Etc.) to a second shape (for example, a square) stepwise, as a result, as shown in FIGS. 14B and 14C, the shape of the three-dimensional face shape polygon is changed to the first shape. It is possible to generate a three-dimensional face shape model of a target shape by gradually deforming the shape from the shape to the second shape.

  That is, by using the face shape modeling method in the present embodiment, for example, the target shape can be finely deformed (blended) with initial data, final data, and intermediate shape data. Further, in the present embodiment, based on the target shape described above, the above-described processing is normally performed on the two-dimensional data by deforming the above-described fragment image and further mapping by changing the curvature or the like according to the face shape. It can be extended to a three-dimensional skin shape model and applied to various simulations.

  FIG. 15 is a diagram illustrating a correspondence relationship between the target shape and the three-dimensional face shape model. In the example of FIG. 15, a three-dimensional face shape polygon to which a fragment image has not been mapped is shown, but a three-dimensional face shape model to which a fragment image is mapped may be displayed.

  In this embodiment, as shown in FIG. 15, a target shape deformed into a predetermined shape (for example, a round shape, a square shape, a triangle, and an inverted triangle) is shown in the up, down, left, and right directions, and a target shape is changed to another target shape. On the other hand, it is possible to map content that has been transformed in stages. In the present embodiment, the target shape itself can be mixed with other target shapes and deformed (blended).

  Thus, until now, when generating face shape models of various patterns, it was necessary to edit each point of data, but by setting the target shape as described above, it can be easily deformed And you can blend intermediate data. Further, by applying the present embodiment to map as shown in FIG. 15, it can be applied to a face standing map used for analysis / evaluation of a user's face, for example. Furthermore, by deforming the fragment image according to the target shape and mapping it to the three-dimensional face shape polygon, it is possible to generate a highly accurate three-dimensional face shape model.

  When applied to the feature map, parameters can be set based on, for example, the skeletal system (frontal bone, cheekbone, front jaw bone, mental shell, etc.), and input curves, straight lines, children, adults, etc. By applying various conditions such as the circle, square, triangle, and inverted triangle shown in FIG. 15, the face shape modeling can be processed in association with the feature map. The feature map means, for example, a map shown in Japanese Patent No. 3529954 and Japanese Patent No. 3614783, but is not limited thereto.

<Makeup skin simulation with skin and face shape>
FIG. 16 is a diagram for explaining a second application example to which the present embodiment is applied. The example of FIG. 16 shows an application example in the case of simulating a difference in appearance under the influence of a change in texture shape and a change in face shape.

  For example, FIG. 16 shows an example in which the effect of the texture and face shape of “gloss cover power” defined as “skin texture 10” is provided to the user as “texture variation”. Specifically, a three-dimensional face shape model of a makeup skin texture face corresponding to “skin texture 10” is generated by the above-described method, and the parameters used when generating the model are changed, for example, gloss cover As an influence, quantitative simulation under the same conditions by a plurality of conditions becomes possible.

  Specifically, as shown in FIG. 16, when “the pore size is large”, the effect is reduced by 20%, and when “the area of the skin is wide”, the effect is 10%. In the case of “weak face roundness”, it is possible to provide the user with the effect of texture and face shape on each texture, such as no effect.

  As described above, according to the present invention, it is possible to generate a skin shape model in which a texture shape and a three-dimensional shape such as a face or a hand are added. Thereby, a quantitative shape simulation can be realized. That is, according to the present invention, the expressive power of the skin shape model is remarkably improved by taking into consideration the effects of skin texture and three-dimensional shape. Further, according to the present invention, skin and face deformation can be quantitatively performed.

  The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to such specific embodiments, and various modifications can be made within the scope of the gist of the present invention described in the claims. Can be changed.

DESCRIPTION OF SYMBOLS 10 Skin shape model production | generation apparatus 11 Input means 12 Output means 13 Memory | storage means 14 Pore production | generation means 15 Area | region division | segmentation means 16 Cuticle skin groove determination means 17 Polygon production means 18 Texture shape modeling means 19 Face shape modeling means (skin shape modeling means)
20 image generation means 21 transmission / reception means 22 control means 31 input device 32 output device 33 drive device 34 auxiliary storage device 35 memory device 36 CPU
37 Network Connection Device 38 Recording Medium 40 Fragment Image 41 Skin Fragment Image 42 3D Face Shape Polygon

Claims (8)

A skin shape model generation device that generates a three-dimensional skin shape using a skin shape generated by a predetermined parameter,
Pore generating means for generating a plurality of pores arranged in a predetermined distribution with respect to a preset skin region;
Of the plurality of pores generated by the pore generation means, an area dividing means for connecting adjacent pores and dividing the skin area;
A bursal skin groove determining means for determining the shape of the skin and the skin groove for the region obtained by the region dividing means;
A polygon generating means for generating a polygon of a predetermined shape based on the shape of the pores generated by the pore generating means, and the shapes of the skin and the skin groove determined by the skin mound determining means;
A texture shape modeling means for modeling the texture shape of the skin by parameter information obtained from the polygon shape obtained by the polygon generating means;
A skin shape model generating apparatus comprising: a skin shape modeling means for generating a skin shape model by mapping the skin shape obtained by the texture shape modeling means in correspondence with a predetermined three-dimensional shape part. . Image generating means for generating a skin shape model image modeled by the skin shape modeling means;
The skin shape model generation apparatus according to claim 1, wherein the image generation unit includes at least one of enlargement, reduction, and rotation in a predetermined direction with respect to the skin shape model of the image. The skin shape modeling means includes
The skin shape model generation apparatus according to claim 1 or 2, wherein the skin shape model and the curvature of the skin are deformed and mapped in correspondence with the predetermined three-dimensional shape portion. The skin shape modeling means includes
2. The skin shape is divided into predetermined regions, and mapping is performed using a fragment image obtained by changing the texture shape of the skin generated by the texture shape modeling unit for each divided region. 4. The skin shape model generation apparatus according to any one of items 1 to 3.   The skin shape model generation apparatus according to claim 4, wherein the division is performed for each tendency of change in the texture shape or for each region having a different composition of facial muscles. The polygon generation means includes
6. The skin shape model generation apparatus according to claim 1, wherein only the polygon of the skin mound included in the skin shape element is roughened. A skin shape model generation method for generating a three-dimensional skin shape using a skin shape generated by a predetermined parameter,
A pore generation step for generating a plurality of pores arranged in a predetermined distribution with respect to a preset skin region;
Of the plurality of pores generated by the pore generation step, an area dividing step of connecting adjacent pores and dividing the skin area;
A tibial skin groove determining step for determining the shape of the skin and the skin groove for the region obtained by the region dividing step;
A polygon generation step for generating a polygon of a predetermined shape based on the shape of the pores generated by the pore generation step, and the shapes of the skin and the skin groove determined by the skin mound skin groove determination step;
A texture shape modeling step for modeling the texture shape of the skin based on parameter information obtained from the polygon shape obtained by the polygon generation step;
A skin shape model generation method comprising: a skin shape modeling step for generating a skin shape model by mapping the skin shape obtained by the texture shape modeling step in correspondence with a predetermined three-dimensional shape portion .   The skin shape model generation program for functioning a computer as each means which the skin shape model generation apparatus of any one of Claims 1 thru | or 6 has.