Application of rough sets to image pre-processing for Face detection

Both of face detection and Face recognition play important role in the technology of biologic character identify. During processing of face image, it is indispensable to pre-processing. In this paper, a Pre-processing method for face color image based on rough sets theory is put forward. In this method, the image is divided as foreground and background by condition attribution. In order to extract the skin color regions, foreground is segmented by two kinds of the skin color model, YCrCb and HSV color spaces. Then, the opening and closing morphological operation are used to remove the small regions. Experiment shows the new algorithm has been tested by the computer simulation, in terms of accuracy extracting the skin color, positive rate of face detection and error rate etc. The results show that it can improve accuracy of extracting the skin color and shorten operation time validly. The result of enhanced image is better and satisfies requirement of face detection.