Face Database Retrieval Using Pseudo 2D Hidden Markov Models

Authors:
Stefan Eickeler
Affiliations:
-
Venue:
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Year:
2002

Citing 0
Cited 3

Discriminant Analysis of Stochastic Models and Its Application to Face Recognition

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Combination of Fisher scores and appearance based features for face recognition

WBMA '03 Proceedings of the 2003 ACM SIGMM workshop on Biometrics methods and applications
A novel metrics based on information bottleneck principle for face retrieval

PCM'10 Proceedings of the 11th Pacific Rim conference on Advances in multimedia information processing: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper explores the face database retrieval capabilities of a face recognition system based on Hidden Markov Models (HMM). 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 method presented here 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 25000 different face images, showing that the normalization and the filler models are most suitable for retrieval on a large face database.