18th International Conference on Pattern Recognition (ICPR'06) Volume 3
Kalman Filtering for Robust Identification of Face Images with Varying Expressions and Lighting Conditions
Hong Kong
August 20-August 24
ISBN: 0-7695-2521-0
DOI Bookmark:
http://doi.ieeecomputersociety.org/10.1109/ICPR.2006.736
We propose a novel algorithm for the identification of faces from image samples. The algorithm uses the Kalman filter to identify significant face features. We employ the Kalmanfaces approach on a database of face images that show a variety of different expressions and were recorded under varying lighting conditions. Kalmanfaces show robustness against distortion and outperform the classic Eigenfaces approach in terms of identification performance and algorithm speed.
Citation:
Horst Eidenberger, "Kalman Filtering for Robust Identification of Face Images with Varying Expressions and Lighting Conditions," icpr, vol. 3, pp.1073-1076, 18th International Conference on Pattern Recognition (ICPR'06) Volume 3, 2006
Usage of this product signifies your acceptance of the
Terms of Use.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||