Real-Time Face Detection and Recognition for Video Surveillance Applications

Abstract

Real-time human face detection and recognition from video sequences in surveillance applications is a challenging task due to the variances in background, facial expression and illumination. The face detection approach is based on modest AdaBoost algorithm and can achieve fast, accurate face detection that is robust to changes in illumination and background. The detection stage provides good results maintaining a low computational cost. The recognition stage is based on an improved independent components Analysis approach which has been modified to cope with the video surveillance application. In the recognition stage, the Hausdorff distance is used as a similarity measure between a general face model and possible instances of the object within the image. After the integration of the two stages, several improvements are proposed which increase the face detection and recognition rate and the overall performance of the system. The experimental results demonstrate the significant performance improvement using the proposed approach over others. It can be seen that the proposed method is very efficient and has significant value in application.