Particle filtering in multilevel color context for face detection and tracking in real-time video sequences

A system for parallel face detection, tracking and recognition in real-time video sequences is being developed. The paper describes its face detection and tracking modules. The solution is based on the particle filtering in the Conditional Density Propagation framework of Isard and Blake and utilizes color information at different levels of detail. The use of color makes processing computationally cheap and robust in finding candidates for further processing.