Analysis And Research Of Face-Tracking And Face-Recognition Methods

The technology of face recognition is an active subject in the area of pattern recognition. There are broad applications in the fields of law, business etc. For the particularity of the face image,face recognition also is one of the very difficult problems. There is still much work to do. Active Shape Model is a powerful statistical tool to locate and track facial feature points by shape, which has been improved for many years. However, due to some defects in local appearance model, ASM can suffer from changes in illumination and facial expression changes. Gabor wavelets have been applied in computer vision for many years, their power and ability has been proved in many works. In this paper, we designed so-called G-ASM method, which combines Gabor wavelet and Active Shape Model to locate and track facial points. Compared with traditional ASM, G-ASM bases on Gabor wavelet instead of local appearance model to guess better places for landmarks, which provide accurate guidance for place-guess. Experimental results demonstrate that G-ASM's stronger ability for facial future tracking. The frameworks and algorithm implement of G-ASM is presented in this paper. How accurately a facial point is guessed based on different Gabor Jets searching methods is tested. The performance of G-ASM is subject to the choice of Gabor wavelet. An experiment to explore how four different Gabor wavelets affect the performance of G-ASM is presented. G-ASM use only 2D shape information. Therefore, this approach is generic and applicable to track other textured objects. Eye is the key feature of face image. It is important for recognition to extract eye feature effectively. Regarding the consistency of Gabor function and mammal visual receptive field, the Gabor transforms of eye is used as its feature template, and the eye position is detected quickly by the method of Guass multi-resolution searching. The experiment shows that the method is robust under variations as rotation, tilt, and facial expression. ASM is a useful method to detect geometric features. Gabor transform offers an efficient way of understanding visual information. A new face recognition method is presented based on ASM and Gabor transform. PDM is used to describe face contour and ASM to search for face contour location. Face features are attained from Gabor transform. Experiments show that this method achieves high recognition rate with few training samples and is robust to the variation of lighting and facial expressions.