| 视频序列中的人脸实时跟踪与识别方法 |
| |
| 引用本文： | 徐一华,贾云得,刘万春,杨聪.视频序列中的人脸实时跟踪与识别方法[J].北京理工大学学报(英文版),2002,11(2):203-207. |
| |
| 作者姓名： | 徐一华 贾云得 刘万春 杨聪 |
| |
| 作者单位： | 北京理工大学,计算机科学与工程系,北京,100081 |
| |
| 摘 要： | 集成了基于肤色的人脸跟踪和基于PCA/BPNN(主成分分析/前馈神经网络)的人脸识别技术,提出了一种人脸实时跟踪与识别方法.该方法可以实现复杂背景下的人脸跟踪,并可处理人脸遮挡问题.通过平均视频序列中的多幅人脸图像,获得了很高的正确识别率.该方法在800 MHz主频的微机上实现,系统处理速度达20帧/s.
|
| 关 键 词： | 人脸跟踪 模式识别 基于肤色 本征脸/主成分分析 人工神经网络 |
| 收稿时间： | 2001/5/20 0:00:00 |
Real-Time Face Tracking and Recognition in Video Sequence |
| |
| XU Yi hu,JIA Yun de,LIU Wan chun and YANG Cong.Real-Time Face Tracking and Recognition in Video Sequence[J].Journal of Beijing Institute of Technology,2002,11(2):203-207. |
| |
| Authors: | XU Yi hu JIA Yun de LIU Wan chun and YANG Cong |
| |
| Affiliation: | Department of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China;Department of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China;Department of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China;Department of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China |
| |
| Abstract: | A framework of real time face tracking and recognition is presented, which integrates skin color based tracking and PCA/BPNN (principle component analysis/back propagation neural network) hybrid recognition techniques. The algorithm is able to track the human face against a complex background and also works well when temporary occlusion occurs. We also obtain a very high recognition rate by averaging a number of samples over a long image sequence. The proposed approach has been successfully tested by many experiments, and can operate at 20 frames/s on an 800 MHz PC. |
| |
| Keywords: | face tracking pattern recognition skin color based eigenface/PCA artificial neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京理工大学学报(英文版)》浏览原始摘要信息 |
|
点击此处可从《北京理工大学学报(英文版)》下载全文 |
|
