| Summary: | 碩士 === 國立中正大學 === 電機工程所 === 95 === This thesis presents a face and gesture recognition based human-computer interaction (HCI) system with a single video camera. Different from the conventional communication method between users and machines, we combine head pose and gesture to control the equipments. We can identify the positions of the eyes and the mouth, and use the facial center to estimate the pose of the head. Two new methods are presented in this thesis: automatic gesture area segmentation and orientation normalization of the gesture. It isnot mandatory for the user to keep upright gestures in the regular position, the system
segments and normalizes the gestures automatically. The experiment shows this method is very accurate, and the gesture recognition rate is 93.6%. The user can control a lot of equipments at the same time, including robot control through the wireless network.
|
|---|
