Özörgütlemeli harita ağları ve gri düzey eş oluşum matrisleri ile görüntü bölütleme

Görüntü bölütleme bir görüntünün bir ya da daha fazla karakteristiğe veya özelliğe göre sınıf ya da altküme denilen bölgelerine ayrılması, aynı karakteristiğe sahip, ilgilenilen alanların arka plandan ve diğer alanlardan ayrılarak belirgin hale getirilmesidir. Görüntü işlemede gerçekleştirilen en zor adım görüntü bölütlemedir. Daha sonra yapılacak olan görüntü analizlerinin ve ilgili uygulamaların başarılı olması büyük ölçüde görüntü bölütlemenin başarısına bağlı olmaktadır. Bu çalışmada çeşitli görüntüler özörgütlemeli harita (SOM) ağları ve gri düzey eş oluşum matrisleri (GLCM) kullanılarak bölütlenmiştir. Bu yöntemlerin görüntü bölütleme uygulamalarındaki performansları değerlendirilmiştir. Sonuçta bu yöntemlerin görüntü bölütlenme uygulamalarında %90 başarılı gösterdiği görülmüştür.

Image segmentation using self-organizing maps and gray level co-occurrence matrices

Image segmentation is the separation of an image into segments called classes or subsets, according to one or more characteristics or features, and enhancing areas of interest by separating them from the background and other areas. Image segmentation is the most difficult stage in image processing. The success of subsequent image analysis and related applications depends greatly on the success of image segmentation. In this study images were segmented using self-organizing map (SOM) networks, and gray level co-occurrence matrices (GLCM). The performances of these methods on image segmentation were evaluated. It is seen that these methods showed %90 success on image segmentation applications.

PDF

___

1. Koh, J., Suk, M., Bhandarkar, S.M., “A multilayer Kohonen's self-organizing feature map for range image segmentation”, IEEE International Conference on Neural Networks, San Francisco, CA, USA, vol.3., 1270-1275, 1993.
2. Egmont-Petersen, M., Ridder, D., Handels, H., “Image Processing with Neural Networks-a Review”, Pattern Recognition, Vol.35, 2279-2301, 2002.
3. Murino V., Vernazza G., “Artificial Neural Networks for Image Analysis and Computer Vision”, Image and Vision Computing, Vol.19, Num.9, 583-584, 2001.
4. Kohonen, T., “The Self-Organizing Map”, Proceedings of Institute of Electrical and Electronics Engineers, Vol.78, 1464-1480, 1990.
5. Güler, İ., Demirhan, A., Karakış, R., “Interpretation of MR images using selforganizing maps and knowledge-based expert systems”, Digital Signal Processing, In Press, doi:10.1016/j.dsp.2008.08.002, 2009.
6. Haralick, R.M., Shanmugam, K. ve Dinstein, I., “Textural Features for Image Classification”, IEEE Transactions on Systems, Man and Cybernetics, Vol. SMC-3, No.6, 610-621, 1973.
7. Beliakov, G., James, S. ve Troiano, L., “Texture recognition by using GLCM and various aggregation functions”, IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2008), Hong Kong, 1472-1476, 2008.
8. Baraldi, A., Parmiggiani, F., “An investigation of the textural characteristics associated withgray level cooccurrence matrix statistical parameters”, IEEE Transactions on Geoscience and Remote Sensing, 33(2), 293-304, 1995.
9. Zaim, A., Sawalha, A., Quweider, M., Iglesias, J., Tang, R., “A New Method for Iris Recognition using Gray-Level Coccurence Matrix”, IEEE International Conference on Electro/information Technology, Michigan, U.S.A, 350-353, 2006.
10. Hu, Y., Zhao, C., Wang, H., “Directional Analysis of Texture Images Using Gray Level Co-Occurrence Matrix”, 2008 IEEE Pacific- Asia Workshop on Computational Intelligence and Industrial Application, Wuhan, China, Vol. 2, 277-281, 2008.
11. Amornrit, P., Jouvencel, B., Tomas, S., “A new method of pipeline detection in sonar imagery using Self-Organizing Maps”, IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS 2003), Nevada, Vol.1, 541- 546, 2003.
12. Siqueira, M.L., Gasperin, C.V., Scharcanski, J., Zielinsky, P., Navaux, P.O.A., “Echocardiographic image sequence segmentation using self-organizing maps”, Neural Networks for Signal Processing X, Proceedings of the 2000 IEEE Signal Processing Society Workshop, Sydney, Australia, Vol.2, 594-603, 2000.
13. Zizzari, A., Seiffert, U., Michaelis, B., Gademann, G., Swiderski, S., “Detection of tumor in digital images of the brain”, Proceedings of the International Conference on Signal Processing, Pattern Recognition and Applications, Rhodes, Greece, 132-137, 2001.
14. Kohonen, T., “Self-Organizing Formation of Topologically Correct Feature Maps”, Biological Cybernetics, 43(1), 59-69, 1982.
15. Haykin, S., Neural Networks: A Comprehensive Foundation, Prentice-Hall, New Jersey, 1999.
16. Şengür, A., Türkoğlu, İ., ve İnce, M.C., “Eğiticisiz Yapay Sinir Ağları ile Görüntü Bölütleme Uygulamaları”, IEEE 13. Sinyal İşleme ve İletişim Uygulamaları Kurultayı, (SIU 2005), 271-274, Kayseri, 2005.
17. Kotropoulos, C., Pitas, I., “Self-Organizing Maps and Their Applications in Image Processing, Information Organization, and Retrieval”, Nonlinear Signal and Image Processing, Editör: Barner, K.E, Arce, G.E., CRC Press, 387- 444, 2004.
18. Uriarte, E.A. ve Martín, F.D., “Topology Preservation in SOM”, Proceedings of World Academy Of Science, Engineering And Technology, Vol.15, 187-190, 2006.
19. Gonzales, R.C., Woods, R.E., Digital Image Processing, Prentice Hall, New Jersey, 2002.
20. İnternet: Helsinki University of Technology, Department of Computer Science and Engineering, “SOM Toolbox”, http://www.cis.hut.fi/projects/somtoolbox/, 2005.
21. Vesanto, J., Himberg, J., Alhoniemi, E., Parhankangas, J., “SOM Toolbox for Matlab 5”, Technical Report A57, Neural Networks Research Centre, Helsinki University of Technology, Helsinki, Finland, 2000.