A Face Detection Method Combining Improved AdaBoost Algorithm and Template Matching in Video Sequence

This paper proposes an automatic and robust method to detect human faces from background that is capable of processing frames of video sequence rapidly while achieving high detection rates regardless of scale, rotation and shelter. The field of this work is the incorporation of AdaBoost and self-adaption region of interest to reducing time complexity in testing time. Next template matching is aim to alleviate common problems in conventional face detection using AdaBoost method such as: inconsistent performance due to sensitivity to rotation of head pose and the obscured of other object. In the final step, focusing on the phenomena of overmatching in test time, this paper proposes an error-correction-factor to overcome.