Research On System Of The Face Recognition

With the development of the economy and society, the need of improving the efficiency and security for some jobs becomes more and more important, such as certification testifying and automatic control in some entrance with camera. This makes the face recognition becomes more important. However, the technique of the face recognition is immaturity.This paper makes a good study of the face recognition, including testifying the face from an image, partitioning main area of the face, abstracting the edge of the image, locating the characteristic points, recognizing the same face, etc. I have many new ideas in the study as follows:A method partitioning facial area from an image by 24_bit color is described. It uses the hue of the 24_bit color image to build a mathematical model of color of skin in the way of statistics and distinctness, which could segment the free from the image effectively.A new multi-orientation linear edge detection method based on 24-Bit color image is proposed, which is based on Prewitt operator and Sobel operator.A methoc of segmenting and extracting the mouth from the facial image oased on 24_bit color image is proposed in this paper. At first, we segment the area of the mov.th by using the value vertical and horizontal projection of red pixel. Then we extract the mouth by using the method of edge extraction and red pixel extraction. This method can effectively erase the interference of the shade and the other interference, and extracting the mouth from the image.We locate the characteristic points basing the spinney shape of mouth and eyes. This method is good for its accurateness of the locating. We partition the face into five departments basing the figure of face, and locate the characteristic points in each department. This makes the result of the location is more accurate.We propose a method to recognize the same face by neural network and the nearest distance of the pattern. This method is good for it's more accurate and better compatible.