Estimating Head Pose with Neural Networks-Results on the Pointing 04 ICPR Workshop Evaluation Data

In this paper we report the results of a neural network based approach to head pose esimtation on the evaluation data set provided for the Pointing04 ICPR workshop. In the presented approach, we use neural networks to estimate a person’s horizontal and vertical head orientation from facial images, which automatically were extracted from the provided data set. With our approach, we achieved an average estimation error of 9.5 degrees for pan and 9.7 degrees for tilt estimation with a multi-user system that was trained on images from all 15 people in the database..

[1]  Tomaso Poggio,et al.  Example Based Image Analysis and Synthesis , 1993 .

[2]  Roberto Cipolla,et al.  Non-intrusive gaze tracking for human-computer interaction , 1994 .

[3]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Alex Waibel,et al.  Gaze Tracking Based on Face‐Color , 1995 .

[5]  Alexander H. Waibel,et al.  A real-time face tracker , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[6]  Alex Waibel,et al.  A model-based gaze tracking system , 1996, Proceedings IEEE International Joint Symposia on Intelligence and Systems.

[7]  Alex Pentland,et al.  Parametrized structure from motion for 3D adaptive feedback tracking of faces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Helge J. Ritter,et al.  Recognition of human head orientation based on artificial neural networks , 1998, IEEE Trans. Neural Networks.

[9]  Alexander H. Waibel,et al.  Modeling focus of attention for meeting indexing , 1999, MULTIMEDIA '99.

[10]  Alexander H. Waibel,et al.  From Gaze to Focus of Attention , 1999, VISUAL.

[11]  Alexander H. Waibel,et al.  Simultaneous tracking of head poses in a panoramic view , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  Rainer Stiefelhagen,et al.  Tracking focus of attention in meetings , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.