Fast Face Detection Based on Enhanced AdaBoost

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. Si- mulation 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.

[1]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[2]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[3]  S. Li,et al.  Real-time face detection using boosting in hierarchical feature spaces , 2004, ICPR 2004.

[4]  Antonio Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, CVPR 2004.

[5]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[6]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Lei Wang,et al.  AdaBoost with SVM-based component classifiers , 2008, Eng. Appl. Artif. Intell..

[8]  Peter Auer,et al.  Weak Hypotheses and Boosting for Generic Object Detection and Recognition , 2004, ECCV.

[9]  Paul A. Viola,et al.  Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade , 2001, NIPS.

[10]  Jiří Matas,et al.  Computer Vision - ECCV 2004 , 2004, Lecture Notes in Computer Science.