The Design and Implementation of Algorithms for Human Face Recognition
Student: Yangbo Gu Advisor: Dr. Wenming Cao
Department of Computer Science and Technology
College of Information Engineering
Zhejiang University of Technology
The automatic recognition of human faces is a hot spot in the field of pattern recognition , which has a wide range of potential applications .
As the results of our in-depth research ,two algorithms are proposed : one for face pose adjustment , the other for facial feature extraction and face identification .
Face pose adjustment , as a loop of human face location, is very important in computer face recognition. Chapter 2 of this thesis presents a new approach to automatic face pose adjustment on gray-scale static images with a single face . In a first stage , the right positions of eyes are precisely detected according to several designed parameters which well characterize the complex changes of the gray parameter in and around eyes and the geometrical shape of eyes . During the second stage , based on the location and the symmetry feature of eyes , the inclination angle is calculated and the face position is redressed . The experimentation shows that the algorithm performs very well both in terms of rate and of efficiency . What’s more , due to the precise location of eyes , the apples of the eyes are detected .