Kernel-based face detection and tracking with adaptive control by Kalman filtering

Author

Boumbarov, Ognian ; Sokolov, Strahil ; Petrov, Plamen ; Sachenko, Anatoly ; Kurylyak, Yuriy

Author_Institution

Fac. of Telecommun., Tech. Univ. of Sofia, Sofia, Bulgaria

fYear

2009

fDate

21-23 Sept. 2009

Firstpage

434

Lastpage

439

Abstract

This paper presents an approach to face detection and tracking in video sequences. We use a set of Haar-like features to train a cascade of classifiers. Face-tracking is performed using the mean-shift algorithm. We propose a method for adaptation both of the tracking-window and of the color-distribution model in order to increase robustness to illumination changes of the environment. Minimizing of the number of iterations is achieved by using dynamic prediction with Kalman filter.

Keywords

Haar transforms; Kalman filters; adaptive control; face recognition; image colour analysis; image sequences; learning (artificial intelligence); telecommunication control; tracking filters; video signal processing; Haar-like feature; Kalman filtering; Kernel-based face detection; adaptive control; classifier training; color-distribution model; face tracking; mean-shift algorithm; video sequence; Adaptive control; Adaptive filters; Application software; Face detection; Head; Histograms; Iterative algorithms; Kalman filters; Robustness; Telecommunication computing; Face detection; biometrics; face tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2009. IDAACS 2009. IEEE International Workshop on

Conference_Location

Rende

Print_ISBN

978-1-4244-4901-9

Electronic_ISBN

978-1-4244-4882-1

Type

conf

DOI

10.1109/IDAACS.2009.5342944

Filename

5342944