期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：2
页码：35-46
DOI：10.14257/ijsip.2016.9.2.04
出版社：SERSC
摘要：Target detection has become a common problem to be solved in computer field. Face detection is an important research direction in target detection and a key link in face information processing as well as the premise and foundation of automatic face recognition. Face detection property influences the result of face information recognition directly. This paper improves current face detection algorithms according to traditional AdaBoost algorithm and Sa-AdaBoostSVM algorithm. The experimental result shows that the algorithm in this paper has good robustness for multi-pose and multi-expression face.
关键词：AdaBoost algorithm; face detection; Haar-like feature; multi-pose
