Partial Swarm Optimization for Minimizing Occlusion Problem during Multi-Face Recognition

Visual surveillance in crowded scenes, especially for humans ,has recently been one of the most active research topics in machine vision because of its applications such as deter and response to crime, suspicious activities, terrorism or other illegal activities. One of the most important problems in multiple face tracking is the occlusion problem. The occlusion problem can be overcome by using the partial swarm optimization (PSO) as a tracker in addition to the kalman filter. Kalman filter is used for filtering the frames and also for removing the Gaussian noise. For face tracking in a video sequence, various face tracking algorithms have been proposed however, most of them have a difficulty in finding the initial position and size of a face automatically. In this, we present a fast and robust method for fully automatic multiple face detection and tracking. Using a small number of critical rectangle features selected and trained by various algorithms, we can detect the initial position, size and view of a face correctly. Face tracking and detection will be done for images and also for the recorded videos but not for live video systems. We are extending the face tracking system for the live videos also with the help of new tracker and the new version tools.