Abstract
3D face recognition is an important research topic nowadays. The performance of a face recognition system degrades incredibly due to the variation of facial appearance with different pose, which is well known as one of the bottlenecks in face recognition. Comparing to the bottleneck on 2D face recognition and face synthesis technique, 3D face model has better accuracy and performance than 2D face image on recognition and synthesis. And the first step of 3D face recognition is 3D face modeling. Generating realistic 3D human face models has been widely applied in computer vision and graphics. We have developed a system that constructs textured 3D face models from the depth camera. The system automatically generates a 3D human head model which can be used in many applications, such as 3D face recognition, 3D animation, video games, man-machine interface, and so on. Nowadays, the communication between man and machine is done mainly by the use of devices like keyboard and mouse, which are not natural for man-machine communication. The ideal manner of communication is body language. Hence, gesture recognition of the hand is an extremely attractive method for user-computer interaction. We propose an approach which is based on projective histogram to detect the number of fingers automatically.In this thesis, we use the range camera SR-3000 to acquire the depth information and intensity images. We apply these data to reconstruct 3D face model and recognize hand gestures.