| Summary: | 碩士 === 國立臺灣科技大學 === 電機工程系 === 102 === Nowadays, most of man-machine interfaces are controlled by contact devices such as keyboard, mouse, or touch panel. It will be a future trend of man-machine interface to analyze human behaviors and provide suitable services through contactless interfaces instead of contact interfaces. Man-machine contactless interface can be achieved by pupils detection system. Pupils detection system can detect user’s pupils from the input image by camera and further analyze user’s eyes status (close or open). Then, the pupils detection system can play a key role in contactless man-machine interface.
Face detection conducted by image processing is a crucial part of man-machine interaction. This research is on the basis of face detection to develop a pupils detection system. In the typical face detection system, users need to face the camera without head tilting to make the system operate normally and accurately. Due to this limitation, it is inconvenient in the real practical applications. This research proposes a point-rotation face detection framework. In this framework, we first locate the face candidates by skin tone detection and apply the edge detection on the candidates to complete the localization. Then we search the edge features by radial template. By the symmetricity of faces, our method can correct the face image to the up-right angle. Finally, a frontal face detector is used to determine the existence and the location of faces. After the previous process the face image will be converted to an up-right face image. Then we apply the torque-weight method to extract the eyes region on the face image. At last, the pupils in the eyes region are detected by using YUV color space. By the proposed framework, the users can operate the system more instinctively and easily.
|
|---|
