[Back]

H. Eidenberger:
"Kalman Filtering for Robust Identification of Face Images with Varying Expressions and Lighting Conditions";
Talk: IAPR ICPR 2006, Hongkong, China; 2006-08-13 - 2006-08-15; in: "IAPR ICPR 2006 Proceedings", (2006).

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.