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

Author
Keywords
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.
Year of Publication
2016
Journal
International Journal of Interactive Multimedia and Artificial Intelligence
Volume
4
Issue
Special Issue on Artificial Intelligence Underpinning
Number
1
Number of Pages
11-14
Date Published
09/2016
ISSN Number
1989-1660
Citation Key
URL
http://www.ijimai.org/JOURNAL/sites/default/files/files/2016/02/ijimai20164_1_2_pdf_27472.pdf
DOI
10.9781/ijimai.2016.412
Attachment