Analysis of Supervised Learners to Extract Knowledge of Lighting Angels in Face Images
Subject Areas : electrical and computer engineering
S. Naderi
1
,
N. Moghadam Charkari
2
,
E. Kabir
3
1 -
2 - Tarbiat Modares University
3 - Tarbiat Modares University
Keywords: Bayes DCT decision tree lighting angles Supervised learning SVM,
Abstract :
Variation of Light intensity and its direction have been the main challenges in many face recognition systems that lead to the different normal and abnormal shadows. Today, various methods are presented for face recognition under different lighting conditions which require previous knowledge about Light source and the angle of radiation as well. In this paper, a new approach is proposed to extract the knowledge of/about the lighting angle/direction in face images based on learning techniques. At First, some effective coefficients on lighting variation are extracted on DCT domain. They will be used to determine lighting classes after normalization. Then, three different learning algorithms, Decision tree, SVM, and WAODE (Weightily Averaged One-Dependence Estimators) are used to learn the lighting classes. The algorithms have been tested on the well known YaleB and Extended Yale face databases. The comparative results indicate that the SVM achieves the best average accuracy for classification. On the other hand, WAODE Bayesian approach attains the better accuracy in classes with large lighting angle because of its resistance against data loss.
[1] T. Chen, W. Yin, X. S. Zhou, D. Comaniciu, and T. S. Huang, "Total variation models for variable lighting face recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1519-1524, Sep. 2006.
[2] [2] J. Ruiz-del-Solar, and J. Quinteros, "Illumination compensation and normalization in eigenspace-based face recognition: a comparative study of different pre-processing approaches," Pattern Recognition Letters, vol. 29, no. 14, pp. 1966-1979, Oct. 2008.
[3] [3] O. Arandjelovic and R. Cipolla, "A methodology for rapid illumination - invariant face recognition using image processing filters," Computer Vision and Image Understanding, vol. 113, no. 2, pp. 159-171, Feb. 2009.
[4] [4] Y. K. Park, S. L. Park, and J. Kim,, "Retinex method based on adaptive smoothing for illumination invariant face recognition," Signal Processing, vol. 88, no. 8, pp. 1929-1945, Aug. 2008.
[5] S. I. Choi, Ch. Kim, C. H. Choi, "Shadow compensation in 2D images for face recognition," Pattern Recognition, vol. 40, no. 7, pp. 2118-2125, Jul. 2007.
[6] [6] A. Franco, L. Nanni, "Fusion of classifiers for illumination robust face recognition," Expert Systems with Application, vol. 36, no.5, pp. 8946-8954, Jul. 2009.
[7] A. S. Georghiades, P. N. Belhumeur, and D. J. Kriegman, "From few to many: illumination cone models for face recognition under differing pose and lighting," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 643-660, Jun. 2001.
[8] Y. Adini, Y. Moses, and S. Ullman, "Face recognition: the problem of compensating for changes in illumination direction," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 721-732, Jul. 1997.
[9] B. K. P. Horn, "Determining lightness from an image," Computer Graphics and Image Processing, vol. 3, no. 1, pp. 277-299, Dec. 1974.
[10] W. Chen, M. J. Er, and S. Wu, "Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain," IEEE Trans. on Systems, Man, and Cybernetics Part B: Cybernetics, vol. 36, no. 2, pp. 458-466, Apr. 2006.
[11] ش. نادري، ن. ا. مقدم چركري و م. ش. معين، "روشي جديد براي كاهش تأثير تغييرات نور در بازدهي سيستمهاي بازشناسي چهره،" پانزدهمين كنفرانس مهندسي برق ايران،صص. 176-182، ارديبهشت 1386.
[12] E. Kirkosa, C. Spathisb, and Y. Manolopoulosc, "Support vector machines, decision trees and neural networks for auditor selection," J. of Computational Methods in Sciences and Engineering Archive, vol. 8, no. 3, pp. 213-224, Aug. 2008.
[13] M. W. Kattan and R. B. Cooper, "A simulation of factors affecting machine learning techniques: an examination of partitioning and class proportions," Omega Int. J. Management Science, vol. 28, no. 5, pp. 501-512, Oct. 2000.
[14] T. S. Lim, W. Y. Loh, and Y. S. Shih, "A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms," Machine Learning, vol. 40, no. 3, pp. 203-228, Sep. 2000.
[15] S. B. Kotsiantis, "Supervised machine learning: a review of classification techniques," Informatica, vol. 31, no. 3, pp. 249-268, Oct. 2007.
[16] G. H. John and P. Langley, "Estimating continuous distributions in bayesian classifiers," in Proc. 11th Conf. on Uncertainty in Artificial Intelligence, pp. 338-345, 18-20 Aug. 1995.
[17] G. Webb, J. Boughton, and Z. Wang, "Not so naive bayes: aggregating one-dependence estimators," Machine Learning J., vol. 58, no. 1, pp. 5-24, Jan. 2005.
[18] L. Jiang and H. Zhang, "Weightily averaged one - dependence estimators," in Proc. of the 9th Biennial Pacific Rim International Conf. on Artificial Intelligence, PRICAI'06, pp. 970-974, 7–11 Aug. 2006.
[19] H. Zhang and L. Jiang, "Hidden naive bayes," in Proc. 12th National Conf. on Artificial Intelligence, pp. 919-924, Pittsburgh, Pennsylvania, US, 9-13 Jul. 2005.
[20] "WEKA: Waikato environment for knowledge analysis", http://www.cs.waikato.ac.nz/ml/weka.
[21] J. R. Quinlan, "Discovering Rules by Induction from large collections of examples," in Expert Systems in the Micro-Electronic Age, D. Michie, ed. , pp. 168-201, 1979.
[22] S. L. Salzberg, "Book Review: C4.5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993," Machine Learning, vol. 16, no. 3, pp. 235-240, Sep. 1994.
[23] W. W. Cohen, "Fast effective rule induction," in Proc. of 12th Int. Conf. on Machine Learning, pp. 115-123, Lake Tahoe, CA, US, Jul. 1995.
[24] P. Winston, "C4.5 Tutorial, http://www2.cs.uregina.ca /~dbd/cs831/notes/ml/dtrees/c4.5/tutorial.html", 1992.
