Optimizing Fuzzy Rule Base for Illumination Compensation in Face Recognition using Genetic Algorithms

  • Bima Sena Bayu Dewantara Electronic Engineering Polytechnic Institute of Surabaya
  • Jun Miura Toyohashi University of Technology


Fuzzy rule optimization is a challenging step in the development of a fuzzy model. A simple two inputs fuzzy model may have thousands of combination of fuzzy rules when it deals with large number of input variations. Intuitively and trialâ€error determination of fuzzy rule is very difficult. This paper addresses the problem of optimizing Fuzzy rule using Genetic Algorithm to compensate illumination effect in face recognition. Since uneven illumination contributes negative effects to the performance of face recognition, those effects must be compensated. We have developed a novel algorithmbased on a reflectance model to compensate the effect of illumination for human face recognition. We build a pair of model from a single image and reason those modelsusing Fuzzy.Fuzzy rule, then, is optimized using Genetic Algorithm. This approachspendsless computation cost by still keepinga high performance. Based on the experimental result, we can show that our algorithm is feasiblefor recognizing desired person under variable lighting conditions with faster computation time.

Keywords: Face recognition, harsh illumination, reflectance model, fuzzy, genetic algorithm


Download data is not yet available.


L.A. Zadeh, Outline of a New Approach to The Analysis of Complex Systems and Decision Processes, IEEE transactions Systems, Man, Cybernetics, SMCâ€3, pp. 28â€44, 1973.

J.H. Holland, Genetic Algorithms, Scientific American, pp.66â€72, 1992.

B.S.B Dewantara, J. Miura, Fuzzyâ€based Illumination Normalization for Face Recognition, IEEE Workshop on ARSO, pp. 131â€136, 2013.

G.P. Nam, K.R. Park, New Fuzzyâ€based Retinex Method for the Illumination Compensation of Face Recognition, Int. Journal of Advanced Robotic System. Vol. 9, pp.103, 2012.

Y.K. Park, S.L. Park, J.K. Kim, Retinex Method Based on Adaptive Smoothing for Illumination Invariant Face Recognition, Signal Processing, Vol. 88, pp.1929â€1945, 2008.

C.A. Perez, L.E. Castillo, Illumination Compensation for Face Recognition based on Genetic Optimization of the Selfâ€Quotient Image Method, International Symposium on Optomechatronic Technologies, pp.322â€327, 2009.

K.R. Singh, M.A. Zaveri, M.M. Raghuwanshi, Rough Membership Function Based Illumination Classifier for Illumination Invariant Face Recognition, Applied Soft Computing, Vol. 12, pp.4105â€4117, 2013.

E.H. Mamdani, Application Of Fuzzy Logic To Approximate Reasoning Using Linguistic Synthesis, IEEE Transactions on Computer C, Vol. 26, No. 12, pp.1182â€1191, 1977.

R. Guo, Q. Dai, D. Hoeim, Singleâ€Image Shadow Detection and Removal using Paired Regions, IEEE Conference on Computer Vision and Pattern Recognition, pp.2033â€2040, 2011.

P. Peer, F. Solina, An Automatic Human Face Detection Method, Proceedings of the 4th Computer Vision Winter Workshop. Pp.122â€130, 1999.

A. Elgammal, C. Muang, D. Hu, Skin Detection †A Short Tutorial, Encyclopedia of Biometrics by Springerâ€Verlag Berlin Heidelberg, 2009.

G. Grove, C. Zerweck, J. Damia, Human Skin Coloration using the RGB Color Space Model, The 4th International Symposium of L'Oreal Institute for Ethnic Hair and Skin Research, 2007.

A.S. Georghiades, P.N. Belhumeur, D.J. Kriegman, From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose, IEEE Trans. Pattern Analysis and Machine Intelligence. Vol. 23, No. 6, pp.643â€660, 2001.

B. Weyrauch, J. Huang, B. Heisele, V. Blanz, Componentâ€based Face Recognition with 3D Morphable Models, Int. Conf. on CVPR Workshop, pp.85, 2004.

M.A. Turk, A.P. Pentland, Eigenfaces for Recognition, Journal of Cognitive and Neuroscience, Vol. 3, pp.71â€86, 1991.

How to Cite
Dewantara, B. S. B., & Miura, J. (2014). Optimizing Fuzzy Rule Base for Illumination Compensation in Face Recognition using Genetic Algorithms. EMITTER International Journal of Engineering Technology, 2(2), 62-79. https://doi.org/10.24003/emitter.v2i2.27