Frontal human face detection using skin detection,face matching and haarcascade

Human face detection one of the most important fields that attract searches since a long time ago until now because of the huge number of applications that benefit from face detection and recognition like crowd surveillance, Attendance System, ATM and other. In this paper we propose a method of frontal face detection that consists in general from two steps human skin detection and human face matching. For human skin detection we suppose ranges for skin color in two color spaces YCbCr and HSV because RGB model affect to the changes of luminance and in this space we cannot separate it from the color information .For getting almost clear image and getting right information from the image we apply blurring techniques (Median and Bilateral) and morphological transformations to delete the noises (Dilation, Erosion, Opening..). After we get the skin region we find the contours after converting the image to black and white .The contour region that contains at least two contours inside it (two eyes) presents the region that contains absolutely the face. After that we apply face matching using template of frontal human face .At last we compare the model with haarcascade classifier and combine the skin detection and haarcascade and get the results.