Kalman Filtering for Illumination-invariant Face Recognition

Abstract

We propose a novel algorithm for the identification of faces from image samples. The algorithm uses the Kalman filter to identify significant facial traits. Kalmanfaces are compact visual models that represent the invariant proportions of face classes. We employ the Kalmanfaces approach on the Physics-based Face Database (provided by the University of Oulu), a collection of face images that were recorded under varying illumination conditions. Kalman faces show robustness against luminance changes and outperform the classic Eigenfaces approach in terms of identification performance and algorithm speed. The paper discusses Kalmanfaces extraction, application, tunable parameters, experimental results and related work on Kalman filter application in face recognition.

Reference

H. Eidenberger: "Kalman Filtering for Illumination-invariant Face Recognition"; Talk: IEEE ELMAR 2006, Zadar, Croatia; 06-01-2006 - 06-04-2006; in: "Proceedings IEEE ELMAR 2006", (2006).

BibTeX

@inproceedings{TUW-140027, author = {Eidenberger, Horst}, title = {Kalman Filtering for Illumination-invariant Face Recognition}, booktitle = {Proceedings IEEE ELMAR 2006}, year = {2006}, keywords = {Face Recognition, Kalman Filtering, Eigenfaces, Statistical Mean, Face Databases}, note = {talk: IEEE ELMAR 2006, Zadar, Croatia; 2006-06-01 -- 2006-06-04} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.