发明名称 |
Model-based coding/decoding method and system |
摘要 |
A processing of causing a face image of a person A as an object of encoding to be deformed in correspondence to expression and motion of a face image of a person B as a reference image. The expression change and the motion from the model wire-frame are treated as fitting information, and this fitting information is made WA1 with respect to a first image of an object for photographing, while is made Wb1 with respect to a second image of an object for photographing. For example, the fitting information from a model wire-frame W00 to an image A1 is Wa1, and the fitting information from the image A1 to the model wire-frame W00 is Wa1. Next, an image A2 into which the first image A1 is caused to be deformed by a texture Ta1 of the first image A1 and a wire-frame function Wb1 Wa1 is obtained through composition. Texture mapping of sticking the texture Ta1 in correspondence to each of small areas of this wire-frame is carried out, whereby the image A2 into which the image A1 is caused to be deformed similarly to an image B1 is obtained through composition.
|
申请公布号 |
US5926575(A) |
申请公布日期 |
1999.07.20 |
申请号 |
US19960746291 |
申请日期 |
1996.11.07 |
申请人 |
TELECOMMUNICATIONS ADVANCEMENT ORGANIZATION OF JAPAN;KABUSHIKI KAISHA TOSHIBA |
发明人 |
OHZEKI, KAZUO;HARASHIMA, HIROSHI;KANEKO, MASAHIDE;SAITO, TAKAHIRO |
分类号 |
H04N7/32;G06T9/00;H03M7/30;(IPC1-7):G06K9/46 |
主分类号 |
H04N7/32 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|