A New Combination of Local Appearance Based Methods for Face Recognition under Varying Lighting Conditions

Authors:
Heydi Méndez-Vázquez;Edel García-Reyes;Yadira Condes-Molleda
Affiliations:
Pattern Recognition Department, Advanced Technologies Application Center, Siboney, Cuba 12200;Pattern Recognition Department, Advanced Technologies Application Center, Siboney, Cuba 12200;Pattern Recognition Department, Advanced Technologies Application Center, Siboney, Cuba 12200
Venue:
CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Year:
2008

Citing 6
Cited 3

From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Using the Discrete Cosine Transform

International Journal of Computer Vision - Special issue: Research at McGill University
Handbook of Face Recognition

Handbook of Face Recognition
Local Binary Patterns as an Image Preprocessing for Face Authentication

FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Face recognition from a single image per person: A survey

Pattern Recognition
Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

On combining local DCT with preprocessing sequence for face recognition under varying lighting conditions

CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Local binary LDA for face recognition

BioID'11 Proceedings of the COST 2101 European conference on Biometrics and ID management
A novel efficient local illumination compensation method based on DCT in logarithm domain

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a different way of using DCT and LBP to com-pensate for illumination variations in face recognition with only one sample image per person. The sensitiveness to lighting variations of the LBP and DCT methods was investigated and from it emerged the proposed new method, consisting in discarding low-frequency DCT coefficients in the logarithm domain in a local way as a preprocessing step, and applying LBP method to represent the facial features. Experimental results on the Yale B database show that the proposal improves the performance of the original methods and their existing extensions.