Date of Award

2010

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Dr. Gerry Dozier

Abstract

In this thesis, we have Investigated the hybridization of genetic-based feature selection (GEFeS), genetic-based feature weighting (GEFeW) and LBP-based face recognition techniques. The results indicate that feature selection and weighting enhances the overall performance of LBP-based face recognition techniques. In addition, the results show that GEFeS reduces the number of features needed by approximately 50% while obtaining significant improvement in the accuracy. GEFeS improves the accuracy from 70.36 to 96.62 (in the case of LBP-GEFeS) and from 70.71 to 96.43 (in the case of oLBP-GEFeS) respectively.

Download

Share

COinS