Illumination invariant face recognition system

Author

Tosik, C. ; Eleyan, A. ; Salman, M.S.

Author_Institution

Elektrik ve Elektron. Muhendisligi Bolumu, Mevlana Univ., Konya, Turkey

fYear

2013

fDate

24-26 April 2013

Firstpage

1

Lastpage

4

Abstract

One of the main issues that degrades the performance of a face recognition system is the illumination problem. In this paper, we investigated different algorithms as a preprocessing step to overcome the illumination problem. Histogram equalization, discrete cosine transforms and steerable Gaussian filters were applied to face images from Yale face database B for illumination normalization. PCA algorithm was used as a feature extractor. Using this preprocessing step the performance of the system shows significant improvements.

Keywords

Gaussian processes; discrete cosine transforms; face recognition; filtering theory; lighting; principal component analysis; visual databases; PCA algorithm; Yale face database B; discrete cosine transforms; face images; feature extractor; histogram equalization; illumination invariant face recognition system; illumination normalization; illumination problem; performance degradation; preprocessing; steerable Gaussian filters; Discrete cosine transforms; Face; Face recognition; Filtering algorithms; Histograms; Lighting; Principal component analysis; Face recognition; discrete cosine transform; principal component analysis; steerable Gaussian filters;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications Conference (SIU), 2013 21st

Conference_Location

Haspolat

Print_ISBN

978-1-4673-5562-9

Electronic_ISBN

978-1-4673-5561-2

Type

conf

DOI

10.1109/SIU.2013.6531374

Filename

6531374