| Summary: | 碩士 === 南台科技大學 === 機械工程系 === 97 === In this paper, a webcam is used to capture images, and combining image processing and neural network technology to develop a head rotation recognition system. First, to identify the face region, then to find out the locations of eyes and lips, and after that according to the head rotating angle, to identify the centers of gravity of the eyes and lips. Furthermore, three sides of the triangle based on the three centers of gravity are obtained, after appropriate calculations to obtain five characteristics. After normalizing these characteristics and the corresponding rotating angles of head, the database is obtained and is used as the training data of the neural network. The experimental results indicate that, in the same light source, the rotating angle of head from -40 degrees to 40 degrees, the proposed head rotation recognition system can identify the head rotation degree direction.
|
|---|
