Rapid Face Detection in Static Video Using Background Subtraction

This paper presents a method that combines the background subtraction with the Viola-Jones face detector to detect human faces from video sequence captured by a fixed camera. We use a texture based method for background subtraction to extract foreground sub-images for the face detector. It allows the detector to focus on face detection on smaller image regions and thereby reduces its computational cost and lower its false positive rate. Compared to other state-of-the-art techniques, the performance of our method is promising.