Enhanced Face Recognition by Fusion of Global and Local Features under Varying Illumination

Author

Trinh, Tan Dat ; Jin Young Kim ; Seung You Na

Author_Institution

Dept. of ECE, Chonnam Nat. Univ., Gwangju, South Korea

fYear

2014

fDate

28-30 Oct. 2014

Firstpage

1

Lastpage

4

Abstract

We propose a new method to enhance performance of face recognition under varying lightings by applying score-level fusion between global and local Fourier-Mellin Transform (FMT) features based SVM. An optimal method based Particle Swarm Optimization (PSO) is used to find optimal weights to fuse the aforementioned information at score-level. The results on Korean face database demonstrate that our proposed method outperforms standard global feature, local feature and other well-known methods. Specifically, the best recognition rate is, respectively, 89% and 85% for indoor and outdoor images.

Keywords

Fourier transforms; face recognition; particle swarm optimisation; support vector machines; visual databases; FMT features; Fourier-Mellin transform; Korean face database; PSO; face recognition enhancement; global features; indoor images; local features; optimal weights; outdoor images; particle swarm optimization; score-level fusion; varying illumination; varying lightings; Databases; Face; Face recognition; Feature extraction; Lighting; Support vector machines; Transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

IT Convergence and Security (ICITCS), 2014 International Conference on

Conference_Location

Beijing

Type

conf

DOI

10.1109/ICITCS.2014.7021764

Filename

7021764