Normalisasi Iluminasi Citra Wajah Dengan Menggunakan Histogram Remapping Pada Pengenalan Wajah Berbasis Fitur Gabor

Hendra Kusuma, Wirawan Wirawan, Adi Suprijanto

Abstract

Tingkat akurasi dari sistem pengenalan citra wajah yang terkendala variasi iluminasi/pencahayaan sangat bergantung pada seberapa baik pengolahan awal yang dilakukan pada citra input. Pada dasarnya prosedur pengolahan awal pada citra wajah adalah proses normalisasi yang dilakukan agar citra-citra wajah dengan variasi iluminasi yang besar menjadi citra-citra wajah dengan iluminasi yang relatif sama. Pada makalah ini akan diterapkan suatu pendekatan sederhana namun efektif pada pemrosesan awal dengan menggunakan penataan ulang histogram citra-citra wajah (histogram remapping). Penerapan dilakukan pada teknik pengenalan wajah berbasis fitur Gabor dan bertujuan menunjukan pengaruhnya terhadap perbaikan tingkat akurasi. Untuk menunjukan efektifitas dan keandalan dari penerapan histogram remapping tersebut maka dilakukan uji coba dengan menggunakan basis data wajah Yale-B. Hasil yang dicapai menunjukkan bahwa teknik pengenalan citra wajah berbasis fitur Gabor dengan penataan ulang histogram, robust terhadap variasi iluminasi/pencahayaan.

Full Text:

PDF

References

Adini, Y., Moses, Y., and Ullman, S., “Face Recognition: The Problem of Compensating for Changes in Illumination Direction”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 19 (7), 1997, pp. 721-732.

Heusch, G., Cardinaux, F., and Marcel S. “Lighting Normalization Algorithms for Face Verification”. IDIAP-com, March 2005.

Chen, W., Er, M.J., and Wu, S. “Illumination Compensation and Normalization for Robust Face Recognition Using Discrete Cosine Transform in Logarithmic Domain”. IEEE Transactions on Systems, Man and Cybernetics – part B, 36(2), 2006, pp. 458-466.

Zou, X.. Kittler, J., and Messer, K., "Illumination Invariant Face Recognition: A Survey," Biometrics: Theory, Applications, and Systems”,BTAS2007. First IEEE International Conference on, Crystal City, VA, 27-29 Sept. 2007, pp. 1-8.

Štruc, V., Žibert, J., and Pavešid, N. (2009). Histogram Remapping as Preprocessing Step for Robust Face Recognition. WSEAS Transactions on Information Science and Applications, 6(3), 520-529

Pelecanos, J., and Sridharam, S. (2001). Feature Warping for Robust Speaker Verification. In: Proc. of the Speaker Recognition Workshop Odyssey, pp. 213–-218.

Gonzalez, R.C., and Woods, R.E. (2002). Digital Image Processing, 2ndEdition, Prentice Hall.

Struc, V., and Pavesic, N.,“From Gabor Magnitude to Gabor Phase Features: Tackling the Problem of Face Recognition under Severe Illumination Changes”, Face Recognition, Milos Oravec, InTech, http://www. intechopen.com/books/face-recognition/, 2010.

Liu, C., Wechsler, H., “Gabor Feature Based Classification Using the EnhancedFisher Linear Discriminant Model for Face Recognition”, IEEE Trans. Image Processing, Vol. 11, 2002, pp.467-476

Shen, L., and Bai, L., “A review of Gabor wavelets for face recognition,”Pattern Analysis and Applications, vol. 9, no. 2, 2006, pp. 273–292.

Turk, M. and Pentland, A. Eigenfaces for Recognition. Journal of Cognitive Neuroscience. 1991; Vol. 3 :71-86.

Zhao, W., Krishnaswamy, A., Chellapa, R., Swets, D. L., & Weng, J. J. Discriminant Analysis of Principal Components for Face Recognition. In H.Wechsler, P. J. Phillips, V. Bruce, F. F. Soulie, & Y. P. Huang. Editors. Face Recognition: From Theory to Applications. CAR-TR-914 ed. Springer-Verlag; 1998 : 73-85.

Jian, L., Shaohua, Z., & Shekhar, C. A Comparison Of Subspace Analysis For Face Recognition. IEEE International Conference on Acoustics & Speech Signal Processing, Hong Kong, 2003;Vol.3: 121-4.

Swets DL, Weng JJ. Using discriminant eigenfeatures for image retrieval. IEEE Transactions onPattern Analysis and Machine Intelligence. 1996; 18 : 831-836.

Kusuma H, Wirawan W, Soeprijanto A. “Gabor-based face recognition with illumination variation using subspace-linear discriminant analysis”, TELKOMNIKA (Telecommunication Computing Electronics and Control). Mar 2012; 10(1): pp. 119-28.

Refbacks

  • There are currently no refbacks.