会议专题

An Improved Face Detection Classifier Based On AdaBoost Algorithm

As an important research field, face detection has been highly paid attentions by researchers. It has theoretical value and application value in computer vision and pattern recognition technologies. Aimed at the problems in face recognition over-training phenomenon, this paper presents an improved sample training classifier, just considering the feature value uncertainty nearby the threshold, and these features corresponding samples adopted a new weight updating method. Experimental results show that the improved classifier can obtain high face detection rates than traditional algorithms.

face detection AdaBoost algorithm over-training classifier

Mingming Liu Guangmin Wu Si Wen Jianming Chen

Depart, of Physics, Faculty of Basic Sci. and Tech., Kunming Uni. of Sci. and Tech., 650500 Kunming, China

国际会议

2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

上海

英文

85-89

2011-10-15(万方平台首次上网日期,不代表论文的发表时间)