Publication

Abstract : Rapid and tough trackingTrackingof multiple faces have many crucial applications in various fields like video surveillance and video conferencing. Hence, it gained lot of momentum from computer vision researchers. Initialization, tracking and display are the three important steps in real-time tracking of multiple faces in high-resolution videos. Out of which, tracking is quite intensive in computation. Object detection and tracking are important in many computer vision applications including activity recognition, automotive safety, and surveillance. In this paper, a computational model of real-time face tracking has been presented. The tracking problem into three parts: the region extractor is based on the integration of skin-color, motion, and silhouette features, while the face detectorFace detectionuses a simple, rule-based face detection algorithm, and SVMSupport Vector Machine (SVM). Real-time detection and tracking implementation has been carried out and results presented.