Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Face database retrieval using pseudo 2D hidden Markov models

: Eickeler, S.


IEEE Computer Society, Technical Committee on Machine Intelligence and Pattern Analysis:
Fifth IEEE International Conference on Automatic Face and Gesture Recognition 2002. Proceedings : 20 - 21 May 2002, Washington, D.C.
Los Alamitos, Calif.: IEEE Computer Society, 2002
ISBN: 0-7695-1602-5
International Conference on Automatic Face and Gesture Recognition (AFGR) <5, 2002, Washington/DC>
Conference Paper
Fraunhofer IMK ( IAIS) ()
face database retrieval; pseudo-2D hidden Markov model; face recognition system; database image ranking; large database; confidence measure; confidence approximation; normalization model; filler model

This paper explores the face database retrieval capabilities of a face recognition system based on hidden Markov models (HMMs). A new HMM-based measure to rank images of the database is presented. The method is able to work on a large database. Previous systems for image retrieval based on HMMs were only capable of operating on small databases. The relation of the presented method to confidence measures is pointed out, and five different approximations of the confidence for the task of database retrieval are evaluated. The experiments are carried out on a database of 25,000 different face images, showing that the normalization and filler models are most suitable for retrieval on a large face database.