Face Representation and Tracking Using Gabor Wavelet Networks

This work presents a new method for a human face representation and tracking in video sequences. A discrete face template is represented by linear combination of the continuous 2D odd-Gabor wavelet functions (Gabor Wavelet Network). The weights and 2D parameters (position, scale and orientation) of each wavelet are determined optimally. Using this representation, an effective face tracking method is achieved that is robust to illumination changes and deformations of the face image such as eye blinking and smile.