复杂背景下的人脸检测

Face Detection in Complex Background

提出了一种新的复杂背景下的人脸检测方法。首先，根据图象的灰度直方图，把图象分割成若干个子图象区域，然后分别在这些子图象区域中搜索可能的人脸，进行全局特征－奇异值特征的提取，最后根据特征匹配检验的结果作出决策。

This paper presents a novel method of face detection in complex background. First, The image is divided into several subimages based on the modes of its global histogram; then every possible face in the subimages is found according to some rules; and lastly the decision is made on the basis of the hypothesis test of the distribution of the SVD feature.