Yapay Arı Koloni Algoritması Kullanılarak Görüntü İyileştirme Yönteminin Geliştirilmesi

Görüntü iyileştirme yöntemleri görüntüyü mevcut durumdan, istenilen amaca uygun olarak daha iyi duruma getirmek için kullanılmaktadır. Bu çalışmada dönüşüm fonksiyonu, histogram genişletme ve histogram eşleştirme yöntemleri birlikte uygulanarak yeni bir görüntü iyileştirme yöntemi önerilmiştir. Önerilen bu yöntemin başarısı yapay arı koloni algoritması kullanılarak geliştirilmiştir. Görüntülerin entropi değeri, kenar piksel sayısı ve piksellerin yoğunluğu objektif değerlendirme kriteri olarak kullanılmıştır. Önerilen yapay arı koloni algoritması temelli yöntemin başarısı klasik yöntemlerden histogram genişletme, histogram eşitleme, bi-histogram eşitleme ve dönüşüm fonksiyonu ile ve sezgisel yöntemlerden genetik, diferansiyel gelişim ve parçacık sürü optimizasyon algoritmaları ile karşılaştırılmıştır. Deneysel sonuçlar önerilen yöntem kullanılarak iyileştirilen görüntülerin diğer yöntemler ile iyileştirilen görüntülerden daha yüksek görsel ve bilgi kalitesine sahip olduğunu göstermiştir

Image Using Artificial Bee Colony Algorithm Improvement of Improvement Method

Image enhancement methods are used to process an image so that the result is more suitable than the original image for a specific application. In this paper by combining transform function, histogram stretching and histogram matching a novel image enhancement method is proposed. The performance of the proposed method has been improved by using artificial bee colony algorithm. The image entropy, the number of edge pixels and the intensity of the pixels are used as an objective criterion function. The performance of the proposed artificial bee colony algorithm based method has been compared with the classical techniques such as histogram stretching, histogram equalization, bi-histogram equalization and intensity transformation methods and with the heuristic techniques such as genetic, differential evolution and particle swarm optimization algorithms. Experimental results demonstrate that the images enhanced using by the proposed method have higher visual and the informational quality than the other methods

PDF

___

[1] Irani, M., Peleg, S., 1991. Improving resolution by image registration, CVGIP: Graphical Models and Image Processing, 53(3): 231-239.
[2] Katsaggelos, A. K., Biemond, J., 1985. A general formulation of constrained iterative restoration algorithms, Acoustics, pp. 700-703. Speech and Signal Processing, IEEE International Conference on ICASSP, May, 1985, Florida.
[3] Gonzalez R. C., Woods R. E., 2007. Digital Image Processing, Third Edition. Prentice Hall, United States, 976 pp.
[4] Raju, A., Dwarakish, G.S., Venkat Reddy, D., 2013. A comparitive analysis of histogram equalization based techniques for contrast enhancement and brightness preserving, pp.353-366. International Journal of Signal Process. Image Processing Pattern Recognition
[5] Kim, Y.T., 1997. Contrast enhancement using brightness preserving bi-histogram equalization, pp. 1-8 IEEE Trans. Consum. Electron. 43 (1),
[6] Cho, W., Seo, S., You, J., Kang, S., 2014. Enhancement Technique of Image Contrast using New Histogram Transformation, pp. 52-56. Journal of Computer and Communications.
[7] Ting, C., Wu, B., Chung, M., Chiu, C., Wu, Y., 2015. Visual Contrast Enhancement Algorithm Based on Histogram Equalization pp. 16981-16999. Sensors.
[8] Gupta, B., Tiwari, M., 2015. Minimum mean brightness error contrast enhancement of colorimages using adaptive gamma correction with color preservingframework, pp.1671-1676. Optik
[9] Jenifer, S., Parasuraman, S., Kadirvelu, A., 2016. Contrast enhancement and brightness preserving of digital mammograms using fuzzy clipped contrastlimited adaptive histogram equalization algorithm, pp. 167-177. Applied Soft Computing
[10] Kim, S., Jeon, J., Eom, K., 2016. Image contrast enhancement using entropy scaling in wavelet domain, pp. 1-11, Signal Processing
[11] Poli, R., Cagnoni, S., 1997. Genetic programming with user-driven selection: experiments on the evolution of algorithms for image enhancement, pp. 269- 277 Genetic Programming Proceedings of the Second Annual Conference, July 13-16, 1997, Stanford University. San Francisco.
[12] Munteanu, C., Lazarescu, V., 1999. Evolutionary contrast stretching and detail enhancement of satellite images, pp.94-99. Proceedings of MENDEL’99, June 9-12,1999, Czech Republıc
[13] Saitoh, F., 1999. Image contrast enhancement using genetic algorithm, pp. 899- 904. IEEE International Conference on, October 12-15, 1999, Tokyo
[14] Munteanu, C., and Rosa, A., Towards automatic image enhancement using genetic algorithms, Proceedings of the Congress on Evolutionary Computation, vol.2, Page(s):1535 – 1542, 2000.
[15] Gorai A., Ghosh A., 2009. Gray level Image Enhanced by Partical Swarm Optimization, pp. 72- 77. Nature & Biologically Inspired Computing, December 9-11, 2009.
[16] Draa A., Boaziz A., 2014. An artificial bee colony algorithm for image contrast enhancement. Swarm and Evolutionary Computation 16: 69–84.
[17] Sarangi, P.P., Mishra, B.S.P., Majhi, B., Dehuri, S., 2014. Gray- level image enhancement using differential evolution optimization algorithm, pp. 95- 100. Signal Processing and Integrated Networks (SPIN 2014).
[18] Karaboga, D., 2010 Artificial bee colony algorithm, 5(3):6915, Scholarpedia.
[19] Holland, J.H., Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.
[20] K. Price, R. Storn, 2004, http://www.icsi.berkeley.edu/~storn/code.html
[21] Kennedy, J., Eberhart, R.C. 1995. Particle Swarm pp. 1942-1948, Optimization Proceedings of the IEEE International Conference on Neural Networks, Australia.
[22] Akay, B., 2009. Nümerik Optimizasyon Problemlerinde Yapay Arı Kolonisi (Artificial Bee Colony) Algoritmasının Performans Analizi. Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Doktora Tezi, 301s, Kayseri.