Using hidden Markov models and wavelets for face recognition

Author

Bicego, M. ; Castellani, U. ; Murino, V.

Author_Institution

Dipt. di Inf., Verona Univ., Italy

fYear

2003

fDate

17-19 Sept. 2003

Firstpage

52

Lastpage

56

Abstract

In this paper, a new system for face recognition is proposed, based on hidden Markov models (HMM) and wavelet coding. A sequence of overlapping sub-images is extracted from each face image, computing the wavelet coefficients for each of them. The whole sequence is then modelled by using hidden Markov models. The proposed method is compared with a DCT coefficient-based approach (Kohir et al. (1998)), showing comparable results. By using an accurate model selection procedure, we show that results proposed in Kohir can be improved even more. The obtained results outperform all results presented in the literature on the Olivetti Research Laboratory (ORL) face database, reaching a 100% recognition rate. This performance proves the suitability of HMM to deal with the new JPEG2000 image compression standard.

Keywords

code standards; data compression; face recognition; feature extraction; hidden Markov models; image sequences; transform coding; wavelet transforms; HMM; JPEG2000 image compression standard; ORL face database; Olivetti Research Laboratory; face recognition; hidden Markov models; image extraction; model selection; overlapping sub-image sequence; performance; wavelet coding; wavelet coefficients; wavelets; Biometrics; Discrete cosine transforms; Face recognition; Hidden Markov models; Image coding; Image databases; Laboratories; Lattices; Transform coding; Wavelet coefficients;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Processing, 2003.Proceedings. 12th International Conference on

Print_ISBN

0-7695-1948-2

Type

conf

DOI

10.1109/ICIAP.2003.1234024

Filename

1234024