Kalman Filtering for Robust Identification of Face Images with Varying Expressions and Lighting Conditions

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.

• Type: Conference
• Year: 2006
• Where: ICPR
• Authors: Horst Eidenberger
• Keywords: Algorithm Speed, Computer Vision, ICPR 2006, Kalman Filter, Significant Face Features