Illumination Normalization for Face Recognition and Uneven Background Correction Using Total Variation Based Image Models

Authors:
Terrence Chen;Wotao Yin;Xiang Sean Zhou;Dorin Comaniciu;Thomas S. Huang
Affiliations:
University of Illinois at Urbana Champaign;Columbia University;Siemens Corporate Research;Siemens Corporate Research;University of Illinois at Urbana Champaign
Venue:
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Year:
2005

Citing 0
Cited 16

Total Variation Models for Variable Lighting Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
A comparison of three total variation based texture extraction models

Journal of Visual Communication and Image Representation
Retinex method based on adaptive smoothing for illumination invariant face recognition

Signal Processing
A Gabor Quotient Image for Face Recognition under Varying Illumination

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Fusion of classifiers for illumination robust face recognition

Expert Systems with Applications: An International Journal
Kernel TV-Based Quotient Image Employing Gabor Analysis and Its Application to Face Recognition

IEICE - Transactions on Information and Systems
Retinex Combined with Total Variation for Image Illumination Normalization

ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
An illumination normalization model for face recognition under varied lighting conditions

Pattern Recognition Letters
Shadow compensation based on facial symmetry and image average for robust face recognition

Neurocomputing
Illumination normalization for robust face recognition using discrete wavelet transform

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
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
A new method of illumination normalization for robust face recognition

CIARP'06 Proceedings of the 11th Iberoamerican conference on Progress in Pattern Recognition, Image Analysis and Applications
Image cartoon-texture decomposition and feature selection using the total variation regularized L1 functional

VLSM'05 Proceedings of the Third international conference on Variational, Geometric, and Level Set Methods in Computer Vision
A new coarse-to-fine framework for 3d brain MR image registration

CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
MQI based face recognition under uneven illumination

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Rough membership function based illumination classifier for illumination invariant face recognition

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new algorithm for illumination normalization and uneven background correction in images, utilizing the recently proposed TV+L鹿 model: minimizing the total variation of the output cartoon while subject to anL鹿-norm fidelity term. We give intuitive proofs of its main advantages, including the well-known edge preserving capability, minimal signal distortion, and scale-dependent but intensity-independent foreground extraction. We then propose a novel TV-based quotient image model (TVQI) for illumination normalization, an important preprocessing for face recognition under different lighting conditions. Using this model, we achieve 100% face recognition rate on Yale face database B if the reference images are under good lighting condition and 99.45% if not. These results, compared to the average 65% recognition rate of the quotient image model and the average 95% recognition rate of the more recent self quotient image model, show a clear improvement. In addition, this model requires no training data, no assumption on the light source, and no alignment between different images for illumination normalization. We also present the results of the related applications - uneven background correction for cDNA microarray films and digital microscope images. We believe the proposed works can serve important roles in the related fields.