复杂背景下的彩色图像人脸检测  

The Face Detection in Color Images with Complex Environments

作　　者：李冯[1] 姚莉秀[1] 杨杰[1] 戈新良[1] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200240

出　　处：《上海交通大学学报》2006年第5期778-782,共5页Journal of Shanghai Jiaotong University

基　　金：上海市科委资助项目(03DZ14015)

摘　　要：提出了一种复杂背景下使用肤色模型检测人脸的方法.该方法首先对图像进行光照补偿,然后对肤色模型处理后的二值图像进行分割与合并,并结合先验知识提取出人脸候选区域,最后验证人脸轮廓、眼睛和嘴等特征来判断人脸候选区域是否包含人脸.对1 010幅变光照和复杂背景情况下拍摄的彩色人脸图像进行验证,其检测率达到89.7%.This paper presented a new algorithm for face detection in complex environment from images. The algorithm works by first doing lighting compensation on input image, then it segments and combines skin regions obtained through applying skin model, and extracts face candidates with the aid of heuristic information. Finally, it evaluates the existence of facial features, such as face boundary, eyes and mouth, in those face candidates. The detection rate has achieved 89.7 % when the algorithm is employed to detect 1 010 color face images containing face rotations with complex environment and lighting variances.

关 键 词：人脸检测 特征提取 区域分割合并 光照补偿 肤色模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]