Abstract
Face recognition is a challenge subject in the field of pattern recognition and it has inportant theory and application value.
In this paper,we first introduce the current research,methods and trend on face recognition.Then we respectively discuss face image preprocessing image edge detection, feature extraction and the design of classifiers.
In the course of image preprocessing,the noise in face images are removed by using the method of median filter and the method of edge-keeping filter.Then we sharpen the images with Laplace operator.
In the course of edge detection,we detect images’edge by using Robers operator,Sobel operator,Robinson operator,Log operator and Canny operator,and compare the results if images;edge.The result shows,Canny edge detection operator precege other operators obviously.
During the feature extraction,three new face organ location methods are proposed,by using these methods,we get good results,Then a method base on global and local information is proposed to compose feature vector.apply DCT to the whole face image while applying DCT to eyes area and nose-mouth area.Finally get the upper-left corner of the DCT matrix as feature vector.
In the course of classifiers design,we construct a classifier with ANN classifier.
Finally,the experiment results of face recognition are presented and analyed,The results indicate that the extracted face features are valid and the design of classifier is sound and efficient.