Eye and face detection using SVM

In the real-time automatic face recognition system, accurate face detection is essential and very important part because it has the effect to face recognition performance. In this paper we use color, edge, and binary information to detect eye pair candidate regions from input image, then extract face candidate region with the detected eye pair. We verify both eye pair candidate region and face candidate region using Support Vector Machines(SVM). It is possible to perform fast and reliable face detection because we can protect false detection through this verification process. Experimental results demonstrate that the proposed approach shows very excellent face detection performance over 99.2%.