Image processing device and method for generating three-dimensional character image and recording medium for storing image processing program

• US 6,747,652 B2
• Filed: 05/17/2002
• Issued: 06/08/2004
• Est. Priority Date: 05/17/2001
• Status: Expired due to Fees

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Inoue, Satoru, Konya, Minehiro, Takezawa, Hajime
• Primary Examiner(s): Zimmerman, Mark
• Assistant Examiner(s): MANCUSO, HUEDUNG XUAN CAO
• Application Number:
  US10/146,825
• Publication Number:
  US 20020171648A1
• Time in Patent Office: 753 Days
• Field of Search: 345/474, 345/473, 345/475, 345/419, 382/154, 382/199, 382/153, 382/159, 348/42, 348/39, 348/45, 348/51, 348/46
• US Class Current: 345/474
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 15/04 Texture mapping

Abstract

An image processing device for generating a 3-D character image of the present invention includes: an image input section for inputting a face image; a storage section for prestoring of 3-D models, body images, and information on a direction, position, and size of a face conforming to the body images; a user input section having a position designation means and a body selection means; an image processing section, including a textured image generation means for generating a textured image so as to paste the input image onto the 3-D model, a textured image storage means, a face image generation means, and a combining means for combining a body image and an image generated by the face image generation section so as to generate a 3-D character image; and a display section.

Claims

1. An image processing device for generating a 3-D character image of a target object included in an input image, comprising:

an image input section for inputting a face image;

a storage section for prestoring plurality types of 3-D models of hair and faces, a plurality of body images, and information on a direction, position, and size of a face conforming to the body images;

a user input section having a position designation means for designating an arbitrary position in the image input via the image input section and a body selection means for selecting the body image stored in the storage section;

an image processing section, comprising

a textured image generation means for generating, based on information representing a position designated by the position designation section, a textured image as viewed from a prescribed position and direction having a prescribed size so as to paste the input image onto the 3-D model,

a textured image storage means for storing the textured image generated by the textured image generation section,

a face image generation means for generating a 3-D still head image by rotating a 3-D face model according to the information on a direction, position and size of a face conforming to the body image, painting the hair, and pasting the textured image onto the 3-D face model, and

a combining means for combining a body image selected by the body selection means and an image generated by the face image generation section so as to generate a 3-D character image; and

a display section for displaying the 3-D character image generated by the image processing section.

2. An image processing device according to claim 1, wherein the storage section stores a plurality of hair and face models, and the user input section includes a model selection section for selecting the plurality of hair and face models stored in the storage section.

3. An image processing device according to claim 1, wherein:

the storage section prestores a plurality of body images, which vary with the lapse of time, and information on a direction, position and size of a face conforming to the body images; and

the combining means generates a 3-D animated image by generating a plurality of still images based on the 3-D head image generated by the face image generation means, the plurality of body images, which vary with the lapse of time, and the information on a direction, position and size of a face conforming to the body images.

4. An image processing device according to claim 1, wherein:

the storage section stores vector still image data and information on a direction, position and size of a face for generating a still body image; and

the combining means generates the still body image based on the vector still image data stored in the storage section and combines the 3-D still head image generated by the face image generation section and the still body image based on the information on a direction, position and size of a face for generating the still body image.

5. An image processing device according to claim 1, wherein:

the storage section stores vector or vector graphics animated body image data and information on a direction, position and size of a face for generating an animated body image;

the face image generation section generates a plurality of face images; and

the combining means generates the animated body image based on the vector animated image data stored in the storage section and combines the plurality of face images generated by the face image generation section and the animated body image based on time-series information on a direction, position and size of a face stored in the storage section.

6. An image processing device according to claim 1, further comprising a function of previewing a head image generated by the face image generation means and displayed on the display section for confirmation.

7. An image processing device according to claim 2, wherein even when a hair or face model is changed by the model selection means, by prestoring a textured image in the textured image storage section, the face image generation section can reproduce a head image based on the textured image stored in the textured storage section by rotating the changed hair or face model according to information on a direction, position and size of a face conforming to a body image.

8. An image processing device according to claim 1, wherein even when a body image is changed by the body selection means, by prestoring a textured image in the textured image storage section, the face image generation section can reproduce a head image based on the textured image stored in the textured storage section by rotating head and face models according to information on a direction, position and size of a face conforming to the changed body image.

9. An image processing device according to claim 1, wherein the face image generation section has an antialiasing image reduction function for generating a high quality head image by generating an image larger than a target image and reducing a size of the generated image.

10. An image processing method for generating a 3-D character image of a target object included in an input image, comprising the steps of:

a) inputting a face image via an image input section;

b) storing in a storage section plurality types of 3-D models of hair and faces, a plurality of body images, and information on a direction, position, and size of a face conforming to the body images;

c) designating an arbitrary position in the image input via the image input section;

d) selecting the body image stored in the storage section;

e) generating, based on information representing a position designated by step c), a textured image as viewed from a prescribed position and direction having a prescribed size so as to paste the input image onto the 3-D face model;

f) storing the textured image generated by step d);

g) generating a 3-D still head image by rotating 3-D face and hair models according to the information on a direction, position and size of a face conforming to the body image selected by step d), painting the hair, and pasting the textured image onto the 3-D face model;

h) combining a body image selected by step d) and an image generated by step g) so as to generate a 3-D character image; and

i) displaying the 3-D character image generated by step h).

11. An image processing method according to claim 10, wherein step b) further includes the steps of j) storing a plurality of hair and face models and k) selecting the plurality of hair and face models stored by step b).

12. An image processing method according to claim 10, wherein:

step b) includes prestoring a plurality of body images, which vary with the lapse of time, and information on a direction, position and size of a face conforming to the body images; and

step h) includes generating a 3-D animated image by generating a plurality of still images based on the 3-D still head image generated by step g), the plurality of body images, which vary with the lapse of time, and the information on a direction, position and size of a face conforming to the body images.

13. An image processing method according to claim 10, wherein:

step b) includes storing vector still image data and information on a direction, position and size of a face for generating a still body image; and

step h) includes generating the still body image based on the vector still image data stored by step b) and combining the 3-D still head image generated by step g) and the still body image based on the information on a direction, position and size of a face for generating the still body image.

14. An image processing method according to claim 10, wherein:

step b) includes storing vector or vector graphics animated body image data and information on a direction, position and size of a face for generating an animated body image;

step g) includes generating a plurality of face images; and

step h) includes generating the animated body image based on the vector animated image data stored by step b) and combining the plurality of face images generated by step g) and the animated body image based on time-series information on a direction, position and size of a face stored by step b).

15. An image processing method according to claim 10, further comprising a function of previewing a head image generated by step g) and displayed on a display section for confirmation.

16. An image processing method according to claim 11, wherein even when a hair or face model is changed by step k), by prestoring a textured image in step f), step g) can reproduce a head image based on the textured image stored in step f) by rotating the changed hair or face model according to information on a direction, position and size of a face conforming to a body image.

17. An image processing method according to claim 10, wherein even when a body image is changed by step d), by prestoring a textured image in step f), step g) can reproduce a head image based on the textured image stored in step f) by rotating head and face models according to information on a direction, position and size of a face conforming to the changed body image.

18. An image processing method according to claim 10, wherein step g) further includes an antialiasing image reduction function step for generating a high quality head image by generating an image larger than a target image and reducing a size of the generated image.

19. A computer-readable recording medium which stores an image processing program for executing an image processing method for generating a 3-D character image of a target object included in an input image, the method comprising the steps of:

a) inputting a face image via an image input section;

b) storing in a storage section plurality types of 3-D models of hair and faces, a plurality of body images, and information on a direction, position, and size of a face conforming to the body images;

c) designating an arbitrary position in the image input via the image input section;

d) selecting the body image stored in the storage section;

e) generating, based on information representing a position designated by step c), a textured image as viewed from a prescribed position and direction having a prescribed size so as to paste the input image onto the 3-D face model;

f) storing the textured image generated by step d);

g) generating a 3-D still head image by rotating a 3-D face model according to the information on a direction, position and size of a face conforming to the body image selected by step d), painting the hair, and pasting the textured image onto the 3-D face model;

h) combining a body image selected by step d) and an image generated by step g) so as to generate a 3-D character image; and

i) displaying the 3-D character image generated by step h).