Offline Face Recognition System Based on Gabor- Fisher Descriptors and Hidden Markov Models

Authors

Zineb Elgarrai
Othmane Elmeslouhi
Mustapha Kardouchi
Hakim Allali
Sid-Ahmed Selouani

DOI

10.9781/ijimai.2016.412

Abstract

This paper presents a new offline face recognition system. The proposed system is built on one dimensional left-to- right Hidden Markov Models (1D-HMMs). Facial image features are extracted using Gabor wavelets. The dimensionality of these features is reduced using the Fisher’s Discriminant Analysis method to keep only the most relevant information. Unlike existing techniques using 1D-HMMs, in classification step, the proposed system employs 1D-HMMs to find the relationship between reduced features components directly without any additional segmentation step of interest regions in the face image. The performance evaluation of the proposed method was performed with AR database and the proposed method showed a high recognition rate for this database.

Source Publication

International Journal of Interactive Multimedia and Artificial Intelligence

Recommended Citation

Elgarrai, Zineb; Elmeslouhi, Othmane; Kardouchi, Mustapha; Allali, Hakim; and Selouani, Sid-Ahmed (2016) "Offline Face Recognition System Based on Gabor- Fisher Descriptors and Hidden Markov Models," International Journal of Interactive Multimedia and Artificial Intelligence: Vol. 4: Iss. 1, Article 14.
DOI: 10.9781/ijimai.2016.412
Available at: https://ijimai.researchcommons.org/ijimai/vol4/iss1/14