Face Segmentation And Feature Extraction Techniques

Technology of human face area location and feature extraction in color image is introduced in this paper. Human face location which is the premise of feature extraction means finding the position of human face in the complicated image. Feature extraction means locating the area where the feature belongs and finding the coordinates of these feature. Feature we point out here refers to pupil, canthus, corners of the mouth and corners of the nose.In the first part of this paper, the principle of human face location is introduced: Because human skin color clusters in the color space, we select a appropriate space to construct the skin color model, then skin color area of face is separated. Finally, we use the construction feature of face to locate the face. In the second part of this paper, different algorithm is introduced to locate different feature points. First, grey level projection and edge detection are used to find the coordinates of the pupil. After finding the rectangle area of the eye position, we calculate the center of the rectangle to get the coordinates, then the canthus can be found. Second, to extract the corner of the mouth, the color of the lip is used. After locating the proximate area of the mouth based on the construction feature of face, we separate the area of lip using its color, then the corner of the mouth can be easily found. To locate the position of the corner of the nose, we separate the nose area on the basis that its intensity of luminance is smaller than other parts of its vicinity, then the coordinates can be found based on the feature of the nostril.