The Face Detection Algorithm Based On Skin Color Segmentation Study

Human face detection is to locate the faces and determine their size, position and amount in an image. As the first step of person identification, human-computer interface,intelligent scene supervision system, face detection has been paid much attention and became a very active research branch in pattern recognition and computer vision application areas with its significant value in recent years.This thesis is focus on arbitrary background image which maybe contain human face, and build a research system combines the skin color segmentation, face template matching and filter candidate region by facial characteristic, some experiment have done based on the system and get a serials statistic data.Firstly, we introduce the face detection's background and status in recent years. The main classification of detection method is enumerated too. Then discuss the algorithm about human face detection based on skin color segmentation and affirm by template matching.Shin color is one of most important human face characteristic, The Gaussian Model skin color segmentation under YCbCr chrominance space method is choose by the thesis. The first step is construct the Gaussian Model for skin color under YCbCr and get the likely region of face, then skin color segmentation is carry out with the method of dynamic threshold optimizing.Some methods are used to filtrate the skin regions according to Morphological and general knowledge of human face .The fake regions can be eliminated and the candidate face areas can be obtained, decrease the succeed process work.The average face template is used to verify whether the probable face area is a face indeed. In this phase to solve the problem that the really face have some inclination and size is not always same, this thesis adjust the stand template thought calculate candidate face areas angle and area size. It can promote the veracity of template matching. At same time it avoid use different size template to try multi-times, the algorithm have higher efficiency. We bring forward locate candidate face area by mass center; get more exactly cross correlation between candidate and template.Finally, this thesis build a research system based on skin color segmentation and average face template confirm, and do some experiment on it. The Experimental results show that the system is feasible and effective.