A Fast Method for Localization of Local Illumination Variations and Photometric Normalization in Face Images
In this paper we present a method for the automatic localization of local light variations and its photometric normalization in face images affected by different angles of illumination causing the appearance of specular light. The proposed approach is faster and more efficient that if the same one was carried out on the whole image through the traditional photometric normalization methods (homomorphic filtering, anisotropic smoothing, etc.). The process consists in using of the Adaboosting algorithms for the fast detection of regions affected by specular reflection combined with a normalization method based on the local normalization that standardizes the local mean and variance into the located region. A set of measures are proposed to evaluate the effectiveness of detectors. Finally, results are compared through two experimental schemes to measure how the similarity is affected by illumination changes and how the proposed approach improves the effect caused by these changes.
KeywordsFace Recognition Face Image Lookup Table Face Detection Adaboosting Algorithm
Unable to display preview. Download preview PDF.
- 1.Tolba, A.S., El-Baz, A.H., El-Harby, A.A.: Face Recognition: A Literature Review. International Journal of Signal Processing 2(2) (2005)Google Scholar
- 4.Georghiades, A., Kriegman, D., Belhumeur, P.: From few to many: Generative models for recognition under variable pose and illumination. IEEE PAMI (2001)Google Scholar
- 5.Riklin-Raviv, T., Shashua, A.: The Quotient image: class-based re-rendering and recognition with varying illumination conditions. In: IEEE PAMI (2001)Google Scholar
- 6.Lee, K., Ho, J., Kriegman, D.: 9 Points of Light: Aquiring Subspaces for Face Recognition Under Variable Lighting. In: IEEE Proc. Conf. Computer Vision and Pattern Recognition (2001)Google Scholar
- 7.Viola, P., Jones, M.: Rapid Object Detection Using a Boosted Cascade of Simple Features. Mitsubishi Electric Research Laboratories, Inc. (2004)Google Scholar
- 8.Rainer, L.: Intel License Agreement For Open Source Computer Vision Library (2000), Haarcascade_frontalface_default.xmlGoogle Scholar
- 9.Xiong, G.: A local normalization algorithm that uniformizes the local mean and variance of an image, URL: http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=8303
- 10.Biomedical Imaging Group. Local normalization algorithm, http://bigwww.epfl.ch/demo/j
- 11.Garea, E., Kittler, J., Messer, K., Mendez, H.: An Illumination Insensitive Representation for Face Verification in the Frequency Domain. In: Proc.of ICPR 2006, IEEE (in press, 2006)Google Scholar
- 12.The Yale Face Database, URL: http://cvc.yale.edu/projects/yalefaces/yalefaces.html
- 13.Gonzales, R., Woods, R., Eddins, S.: Digital Image Processing using Matlab. pp. 404–405 Ed Pearson (2004)Google Scholar