Face detection for visual surveillance

Abstract

In this paper, a real-time face detection system for color image sequences is presented. The system applies three different face detection methods and integrates the obtained results to achieve a greater location accuracy. The first method localizes the human head through outline analysis, focusing the attention of the system on a small image area. The second, a skin color method, is applied to the blobs to find skin regions (e.g., faces, hands, etc.). The third. principal component analysis, is used to reduce the dimensionality of the data set and to detect face patterns. Finally. the obtained face locations are fused to increase the detection reliability and to avoid false detections due to occlusions or unfavorable human poses. The proposed approach is used by a video-based surveillance system for monitoring indoor scenes.