Face detection using boosted Cascade of features Using Viola-Jones

During the recent years, high resolution cameras and video streams has had a significant on communication and in entertainment world. This paper describes a face detection frame work which is capable of processing of images extremely fast and achieve high detection rate. There are three key contributions in this paper. First is the a new modified image representation that is called "Integral image" it allows detector to compute very fast. The second one is the classifier which is built by modified AdaBoost, it uses very important features from a very large set of features. The third one is the combination of classifier that is called "cascade". The cascade provides a very effective mechanism that helps achieve high classification with low cpu utilization.

[1]  David J. Marchette,et al.  Fast Face Detection with a Boosted CCCD Classifier , 2003 .

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

[3]  Paul A. Viola,et al.  Fast Multi-view Face Detection , 2003 .

[4]  Jiri Matas,et al.  AdaBoost with totally corrective updates for fast face detection , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[5]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..