| 基于表情活动单元的人脸模型自动适配 |
| |
| 引用本文： | 张惟晓,黄艺,余兆明.基于表情活动单元的人脸模型自动适配[J].南京邮电大学学报(自然科学版),2000,20(2):6-10. |
| |
| 作者姓名： | 张惟晓 黄艺 余兆明 |
| |
| 作者单位： | 南京邮电学院信息工程系,江苏南京,210003 |
| |
| 基金项目： | 基金资助：信息产业部中青年项目 |
| |
| 摘 要： | 基于表情活动单元的人脸模型自动适配是极低码率可视电话模型基编码所必需的。本文提出的算法使用变形模板估计眼睛和嘴巴的特征，利用这些特征用Candide模型对人脸进行适配。本算法对人脸模型的全局适配没有旋转限制，而且表情活动单元的初值决定于模仿适配。算法在视频序列Akiyo和Miss America(GIF，10Hz)上实验、证明了其正确性和有效性。
|
| 关 键 词： | 图像编码 表情活动单元 人脸模型 模型基编码 语义基编码 |
| 文章编号： | 1000-1972(2000)02-0006-05 |
| 修稿时间： | 1999-08-26 |
Automatic Adaptation of a Face Model Using Action Units |
| |
| ZHANG Wei-xiao,HUANG Yi,YU Zhao-ming.Automatic Adaptation of a Face Model Using Action Units[J].Journal of Nanjing University of Posts and Telecommunications,2000,20(2):6-10. |
| |
| Authors: | ZHANG Wei-xiao HUANG Yi YU Zhao-ming |
| |
| Institution: | ZHANG Wei-xiao
,HUANG Yi
,YU Zhao-ming
;(Department of Information Engineering, Nanjing University of Posts and Telecommunicatons, Nanjing 210003, China) |
| |
| Abstract: | The automatic adaptation of a face model using action units is necessary for the model-based coding of videophone sequences at very, low bit rates. In the proposed algorithm, eye and mouth features are firstly estimated using deformable templates. Then,the face model Candide is adapted to these estimated features. The algorithm differs from previous works in the following aspectsthere is no restriction on the rotation for the global adaptation, and initial valnas of action units are determined due to the mimic adaptation. The algorithm has been applied to the test sequences Akiyo and Miss America (CIF, 10 Hz) with high accuracy and efficiency. |
| |
| Keywords: | Image coding Action units Face model Model-based coding Semantic coding |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
