Fast face detection based on enhanced AdaBoost

Abstract

Face detection is studied widely important topic in computer vision and pattern recognition. AdaBoost-cascade learning is advanced algorithms for fast object detection in low cost processing. Despite its great success, several important issues involved in still remain open problems: How to select the most discriminative weak learners and how to optimally combine them. In this work, two novel ideas are proposed for improved AdaBoost-cascade face detection. Firstly, through studying the property of weak classifier, a method of computing threshold is proposed which achieved high detection rate for using fewer weak classifiers. Secondly, selecting discriminative weak learners to optimize the detection performance, this approach maintains the simplicity of evaluation of traditional formulation while being more discriminative and more efficient. Simulation experiments in face detection system are conducted including human frontal faces and clutter our method is superior to conventional AdaBoost in compute efficiency, and increase the classification accuracy of the existing classifiers. © 2012 Springer-Verlag GmbH.