A robust algorithm for 3D head pose estimation

Presents a method to estimate the 3D pose of a human head in an image. To increase the stableness of the pose estimation, we use continuous representations instead of binary images to describe the skin/hair regions in an image. We use them to calculate the geometrical properties such as area, center, and the axis of least inertia of the skin, the hair, and the head regions. Then we use them to estimate the 3D pose of the head.

[1]  Hans Peter Graf,et al.  Robust face feature analysis for automatic speechreading and character animation , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[2]  Larry S. Davis,et al.  Computing 3-D head orientation from a monocular image sequence , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[3]  David Machin,et al.  Real-time facial motion analysis for virtual teleconferencing , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[4]  Christoph von der Malsburg,et al.  Tracking and learning graphs and pose on image sequences of faces , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[5]  Qian Chen,et al.  Face detection by fuzzy pattern matching , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Haiyuan Wu,et al.  A fuzzy-theory-based face detector , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[7]  Alexander Zelinsky,et al.  Real-time visual recognition of facial gestures for human-computer interaction , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[8]  David Machin.  Real-Time Facial Analysis for Virtual Teleconferencing , 1996 .