中文摘要：

针对复杂背景下的多姿态彩色人脸图像,提出了一种基于Adaboost级联分类器和模板匹配相结合的人脸检测算法。利用肤色信息对对图像中的皮肤区域和非皮肤区域进行分割,运用改进后的Adaboost方法定位可能的人脸区域。最后通过模板匹配的方法对检测到的人脸区域进行进一步验证,实现了彩色图像中更精确的人脸定位。在实验中从不同大小、背景、光照、表情和光源方向等方面对多姿态的人脸图像进行了检测,取得了很好的效果,表明了该算法的有效性和实用性。

英文摘要：

A novel technique for detecting faces in multi-pose color images with complex background is proposed. The method combines improved cascaded classifier based on Adaboost with template matching technique. First,skin color information is used to segment the non-skin-color pixels from the image. Then the face candidates are obtained by an improved cascaded classifier based on Adaboost learning algorithm. Finally,template matching technique is carried out to determine whether a candidate area is a human face or not,thus more accurate face detection in color images is realized. This system detects human face in different scales,various poses,different expressions,lighting conditions,and orientation. Experimental results show the proposed system obtains competitive results and good detection performance,which illustrate the effectiveness and availability of the algorithm.