Computer graphics processing and selective visual display system – Computer graphics processing – Animation
Reexamination Certificate
2002-05-17
2004-06-08
Zimmerman, Mark (Department: 2671)
Computer graphics processing and selective visual display system
Computer graphics processing
Animation
C382S154000
Reexamination Certificate
active
06747652
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a three-dimensional character image processing device and method for generating a realistic three-dimensional model by using an image, and to a recording medium for storing an image processing program.
2. Description of the Related Art
Conventionally, various techniques for generating a realistic three-dimensional (hereinafter referred to as “3-D”) character image using a plurality of images have been proposed.
For example, in a 3-D model generation device disclosed in Japanese Laid-Open Patent Publication No. 2001-109907, a 3-D model is transformed so as to conform to an input image by designating positions of specific points in a face image included in the input image. A corresponding relationship between the input image and the 3-D model is calculated so as to generate a textured image such that the generated textured image includes a face image as viewed from the front and pixel values in the textured image are uniform both inside and outside of the outline of the face, thereby generating a natural 3-D character image.
Further, a 3-D model generation device disclosed in Japanese Patent Application No. 11-283387 (Japanese Laid-Open Patent Publication No. 2001-109913) is provided with a means for selecting models corresponding to various parts of a 3-D character image to be generated, so that a posture and a hairstyle of the character in the 3-D character image can be freely selected according to a user's preference.
In the above-described conventional techniques, 3-D models corresponding to various parts, such as a face, hair, a body, etc., are provided so as to generate a realistic 3-D character image using a plurality of images. When generating a face image, calculations for converting the 3-D models into images are simultaneously performed so that positions of the various parts are not inconsistent in a depth direction.
This method requires a great number of calculations in the steps of rotating the models, pasting a textured image on each surface of the models, and realizing consistency of the model surfaces in the depth direction. Therefore, a storage device having a great capacity is required for the calculations. Therefore, in order to generate a realistic 3-D character image using this method, it is necessary to use a computing unit exclusively structured for image processing or a device which includes an image processing program specialized for use in a specific device and incorporated into a personal computer having a general-purpose computing function with high processing ability.
That is, the conventional method cannot be performed by a computing device or a mobile computer, which do not have a storage device with a great capacity, and therefore such a computing device or mobile computer cannot generate a realistic 3-D character image. Further, in the computing device or mobile computer with a relatively low processing ability, which do not have a computing unit for exclusive use in image processing, even if a problem related to the capacity of the storage device is solved, a great deal of time is spent for calculations, making a user of the device feel uncomfortable.
SUMMARY OF THE INVENTION
An image processing device for generating a 3-D character image of a target object included in an input image of the present invention includes: 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, including 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.
An image processing method for generating a 3-D character image of a target object included in an input image of the present invention includes 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).
A computer-readable recording medium of the present invention 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, and the method includes 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).
With the above-described image processing device, method and recording medium of the present invention, a 3-D character image is generated by combining a face image, having an arbitrary direction, position and size, with a body image selected by the body selection means. The face image is generated by designating specific points in a face image input via the image input section using the position designation means and pasting a hair image and the input face image onto 3-D hair and face models. According to the present invention, initially the f
Inoue Satoru
Konya Minehiro
Takezawa Hajime
Cao Huedung X.
Zimmerman Mark
LandOfFree
Image processing device and method for generating... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Image processing device and method for generating..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image processing device and method for generating... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3365733