Detection and Segmentation of Human Face

Abstract: Detection and segmentation of faces from an image is a crucial problem that has gained importance, face detection and segmentation play the main role in the face recognition systems. There are many difficulties should be solved to make the face detection and segmentation algorithm successful. The face skin has special colors range as well as special textures that can be detected by using texture recognition algorithms which recognized skin from the background. In this paper we introduced a new method for face detection and segmentation based on face color, we uses the YCbCr color space as a method to segment image to many regions. Gray level co-occurrence matrix used to extract the important features represent the skin, and then Tamura texture used to remove all the non skin blobs which is recognized as skin by GLCM. The proposed algorithm tested with many images and it was successfully recognize the images with faces from images without faces. The proposed algorithm has high efficient in detected faces and segmented faces from the background. The accuracy of this algorithm more than 99% in detection faces and also segment its. The proposed algorithm forms a prerequisite for any practical verification system using face as the main attribute.

Keywords: segmentation, face detection, GLCM, skin color, Tamura.