Abstract：
A novel real-time and non-wearable human-computer interaction (HCI) method has been proposed based on facial orientation. According to facial biological structure characteristics, an active shape model is employed to locate some feature points in the facial contour instead of some other ones in the facial organs including eyes, mouth, nose, and so on which can be able to overcome the effects of illumination and facial posture variation. In this way, not only can some redundant information be simplified, but also some stable feature points can be gotten that improves the rate of computations and makes HCI in real time. After a 2D facial geometric model being built based on the maximal triangulation of facial contour features, a calibrated Kinect camera is used to map the geometric model into 3D coordinate. In order to determine the interacted targets, the nasal tip point is taken as an origin of coordinate and the normal direction of facial orientation is calculate dynamically by a temporal median filter. Non-wearable and natural HCI modal can be realized in which the user can move freely without wearing any equipment or auxiliary markers when he points at some targets. Besides, the need of comfort and diversity can be meet simultaneously during HCI. Experiment results indicate that the developed approach is efficient and can be used to natural non-wearable HCI.?????
Tag：
点此返回栏目查看更多>>>参考论文
