Research On Eye Location And Face Edge Extraction In Color Image

Automatic Face Recognition (AFR) is a technology for Person authentication by using the digitized facial features. For the past two decades, it has become one of the most challenging research topics in the field of image processing, pattern recognition and computer vision. Automatic Face Recognition have been intensively investigated by researchers and many useful algorithms have been developed. Since faces of different subjects are often similar while face images from the same person often differ quite significantly due to pose, expression variations and lighting conditions, current face recognition systems cannot meet the requirements of many practical applications.This thesis focuses on the research of human eye localization and the edge extraction algorithms of face with good robustness. The positions of two eyes are commonly used for the geometry normalization of a face image. Eye location is thus a very crucial step for the establishment of an FAFRS. The second research focus of this thesis was edge extraction algorithm of face. As the important content of face, the face contour line is a base of many classification methods. In particular, this thesis makes two main contributions detailed below.(1) A new method for the localization of human eyes is presented. The method is based on the character that eyes have higher degree of complexity. Firstly, a search area of the eyes is determined by using the result of horizontal projection of grayscale. Secondly, a lesser area is determined by...