A tied-mixture 2D HMM face recognition system

Author

Othman, H. ; Aboulnasr, T.

Author_Institution

Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont., Canada

Volume

2

fYear

2002

fDate

2002

Firstpage

453

Abstract

In this paper, a simplified 2D second-order hidden Markov model (HMM) with tied state mixtures is applied to the face recognition problem. The mixture of the model states is fully-tied across all models for lower complexity. Tying HMM parameters is a well-known solution for the problem of insufficient training data leading to nonrobust estimation. We show that parameter tying in HMM also enhances the resolution in the case of small model. The performance of the proposed 2D HMM tied-mixture system is studied for the face recognition problem and the expected improved robustness is confirmed.

Keywords

face recognition; hidden Markov models; learning (artificial intelligence); parameter estimation; probability; 2D face recognition; Gaussian kernels; model training; parameter estimation; parameter tying; probability distributions; second-order hidden Markov model; tied-mixture; Character recognition; Face recognition; Hidden Markov models; Information technology; Kernel; Optical character recognition software; Robustness; Speech recognition; Training data; Two dimensional displays;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2002. Proceedings. 16th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-1695-X

Type

conf

DOI

10.1109/ICPR.2002.1048336

Filename

1048336