| 视频中的多视角人脸检测与姿态判别 |
| |
| 引用本文： | 宋红,石峰.视频中的多视角人脸检测与姿态判别[J].计算机辅助设计与图形学学报,2007,19(1):90-95. |
| |
| 作者姓名： | 宋红 石峰 |
| |
| 作者单位： | 北京理工大学计算机科学技术学院,北京,100081 |
| |
| 摘 要： | 提出了一种基于多种信息融合的多视角人脸检测方法.对视频图像通过对称差分算法检测运动区域,利用神经网络肤色模型对运动区域进行肤色识别,将多视角多人脸检测简化在候选区域内;最后通过集成多神经网络,其中每个神经网络负责一定视角的图像,实现了人脸验证,同时可以粗略地判定人脸姿态.实验结果表明该算法可适应不同的光照环境,检测不同大小,不同视角的人脸.
|
| 关 键 词： | 多视角人脸检测 BP神经网络 姿态判别 视频图像 多视角人脸检测 姿态判别 Video Discrimination Pose 不同视角 大小 光照环境 可适应 差分算法 结果 实验 验证 多神经网络 集成 候选区域 简化 多人脸 肤色识别 |
| 收稿时间： | 2006-04-18 |
| 修稿时间： | 2006-04-182006-08-18 |
Multi-View Face Detection and Pose Discrimination in Video |
| |
| Song Hong,Shi Feng.Multi-View Face Detection and Pose Discrimination in Video[J].Journal of Computer-Aided Design & Computer Graphics,2007,19(1):90-95. |
| |
| Authors: | Song Hong Shi Feng |
| |
| Affiliation: | School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081 |
| |
| Abstract: | Symmetrical frame difference was used to detect the motion area and a skin-color segmentation algorithm based on BP neural network was used to extract the face candidates. Then, a combination of multiple neural networks, each corresponding to a certain range of face orientation, is used for face verification as well as for pose discrimination. Experimental results show that the algorithm is robust for human faces under deep-vlew rotation, and is adaptive to various lighting conditions and different face sizes. |
| |
| Keywords: | multi-view face detection BP neural network poses discrimination |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
