Towards a real-time and distributed analysis system for face detection, pose estimation and face-related features

J. Nesvadba¹, A. Hanjalic², P. Fonseca¹, B. Kroon^1,2, H. Celik^1,2 and E. Hendriks²

¹Philips Research, Eindhoven, The Netherlands
²Delft University of Technology, Delft, The Netherlands

The evolution of storage capacity, computation power and connectivity in Consumer-Electronics(CE)-, in-vehicle-, medical-IT- and on-chip- networks allow the implementation of grid-computing-based real-time and distributed face-related analysis systems. A combination of facial-related analysis components - Service Units (SUs) – such as omni-directional face detection, pose estimation, face tracking and facial feature localization provide a necessary set of basic visual descriptors required for advanced facial and human-related feature analysis SUs, such as face recognition and facial-based mood interpretation. Smart reuse of the available computational resources across individual CE devices or in-vehicle- and medical-IT- networks in combination with descriptor databases facilitate the establishment of a powerful analytical system applicable for various domains and applications.

Paper presented at Measuring Behavior 2005 , 5^th International Conference on Methods and Techniques in Behavioral Research, 30 August - 2 September 2005, Wageningen, The Netherlands.

© 2005 Noldus Information Technology bv