基于差分图像的人脸检测与跟踪研究  

Difference Picture Based Face Detection and Tracking

作　　者：俞海珍[1] 史旭华[1] 

机构地区：[1]宁波大学信息科学与工程学院,浙江宁波315211

出　　处：《宁波大学学报（理工版）》2007年第4期425-428,共4页Journal of Ningbo University：Natural Science and Engineering Edition

摘　　要：人脸检测与跟踪是人脸信息处理领域中的一项关键技术,提出了一种可通过自适应阈值分割运动区域,根据人脸几何特征验证得到人脸模板,再运用GA跟踪人脸,并且用M6215摄像头进行实时采集、定位与跟踪的新的快速有效的人脸跟踪方法.实验表明:本系统不仅跟踪速度快,还可以在人的手势变化干扰或背景有干扰的情况下,进行令人满意的人脸检测与跟踪。The face detection and tracking is a key technology in the field of facial information processing. In this paper, a new method is proposed for quick and effective face tracking .An algorithm of image segmentation is developed based on self-adaptive threshold value. Face geometry character are applied to verify very candidate region to acquire real face regions. The detected face is used as matching template in the face tracking with generated algorithms. The final face real-time capture, face detection and tracking are realized with video camera. Experimental results show that this system can quickly carry out the face tracking satisfactorily in various noisy backgrounds.

关 键 词：自适应阂值 人脸定位 遗传算法 人脸跟踪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]