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.