A Fast Face Detection for Video Sequences
Lushen Wu, Peimin Wu, Fanwen Meng · 2010
The paper proposed a fast face detection algorithm which integrates differential algorithm and mosaic rules for videos. The comprehensive algorithm with temporal difference and background difference was used for acquiring and tracking the moving objects, which can accurately locate the target region. In the region, the gray rules based on mosaic image were used for detecting face, in which the integral image was adopted to compute the sum gray value. Then the paper used a new method based on the frequency histogram to combine the detection area, and finally the face position was obtained. The experiment shows that the average detection time is 30 ms/frame and the accuracy rate is high, which is suitable for real-time face detection for different kinds of video images.