摘要
人脸是一个复杂的模式,在图像中自动地对其进行定位和分割是进行人脸识别的第一步。本文提出一种运用肤色信息和模板匹配的人脸检测方法。该方法先进行肤色分割,然后对每一个人脸候选区域进行形状比例的分析,最后进行模板匹配。实验结果表明,该方法对任意背景下,任意姿态及任意数目的人脸检测非常有效。
The human face is a complex pattern. It is the first step for face recognition to find human faces automatically in image. In this paper, an approach to face detection based on skin color and template matching is introduced. First, one method that builds the skin color model is used to segment the face-like regions in a color image.Then, the shape information of each face-like region is used to examine.Finally, the face template is used to match.The experimental results show that the proposed approach is effective to detect human faces of any number with any poses in any background.
出处
《中国测试技术》
CAS
2006年第1期53-55,共3页
CHINA MEASUREMENT & TESTING TECHNOLOGY
关键词
人脸检测
色度空间
肤色分割
模板匹配
Face detection
Chrominance space
Skin color segmentation
Template matching
