Doku tipi imgelerin sınıflandırılması için bir uygulamalı entropi tabanlı dalgacık-yapay sinir ağı sistemi

Günümüzde, doku tipi imgelerin analiz ve sınıflandırılması konusu önemli bir hal almıştır. Doku tipindeki imgelerin sınıflandırılmasında geçmişte karşılaşılan en büyük güçlük, bu tür imgelerin doğru karakterize edilebil- mesi için yeterli yöntemlerin geliştirilememesidir. Ancak son zamanlarda, Gabor süzgeçleri, dalgacık ayrışımları gibi çok çözünürlüklü analiz yöntemlerinin doku tipi imgelerin sınıflandırılmasında diğer klasik yöntemlere göre üstün başarı sağladıkları görülmektedir. Bu çalışmada ise, Brodatz imge albümünden elde edilen 20 adet doku tipi resmin sınıflandırılabilmesi için, uyarlamalı norm entropi tabanlı bir dalgacık-yapay sinir ağı yapısı geliştiril- miştir. Kullanılan yapay sinir ağı çok katmanlı geriye yayılımlı yapıya sahiptir. Yapılan test çalışmalarında geliştirilen yöntemin etkinliği denenmiş ve ortalama % 90 oranında bir tanıma başarısı elde edilmiştir.

A wavelet-artificial neural network system based on adaptive entropy for texture images classification

Nowadays, analysis and classification of texture images analysis and classification becomes an important topic. In the past, greatest difficulty in classification of texture images was the deficiency of enough methods to characterize. Recently, it is seen that, multi-resolution analysis methods such as Gabor filters, wavelet decompositions are superior to other classic methods. In this study, a wavelet-artificial neural network structure based on adaptive norm entropy was developed for classification of the 20 texture images obtained from Brodatz image album. The artificial neural network used in this study has a multi layer, back propagation structure. Efficiency of the developed method was tested showing that an average of %90 recognition success was obtained.

PDF

___

1. Pun, C. ve Lee, M., “Extraction of Shift Invariant Wavelet Features for Classification of Images with Different Sizes”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Cilt:26, No.9,Eylül 2004.
2. Tuceryan, M., ve Jain, A. K., Texture Analysis,Handbook of Pattern Recognition and Computer Vision, 235-276, World Scientific, 1993.
3. Conners R.W., ve Harlow, C.A., “A Theoretical Comparison of Texture Algorithms,” IEEE Trans.Pattern Analysis and Machine Intelligence, Cilt 2, 204-222, Mayıs 1980.
4. Bovik, A., C., Clark, M., ve Geisler, W., S., “Multichannel Texture Analysis Using Localized Spatial Filters,” IEEE Trans. Pattern Analysis and Machine Intelligence, Cilt No: 12, Ocak 1990.
5. Teuner, A., Pichler, O., ve Hosticka, B., J., “Un- supervised Texture Segmentation of Images Using Tuned Matched Gabor Filters, IEEE Trans. Image Processing, Cilt:6, No:4, 863-870, 1995.
6. Chang, T., ve Kuo, C.C.J., “Texture Analysis and Classification with Tree-Structured Wavelet Trans-form”, IEEE Trans. Image Processing, Cilt: 2, 429-441, Nisan 1993.
7. Laine, A., ve Fan, J., “Texture Classification by Wavelet Packet Signatures”, IEEE Trans. Pattern Analysis and Machine Intelligence, Cilt:15, No: 11, 1186-1191, Kasım 1993.
8. Unser, M., “Texture Classification and Segmentation Using Wavelet Frames”, IEEE Trans. Image Proc-essing, Cilt No: 4, 1549-1560, Kasım 1995.
9. Pun, C., ve Lee, M., “Log-Polar Wavelet Energy Signatures for Rotation and Scale Invariant Texture Classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Cilt:25, No:5,Mayıs 2003.
10. Haralick, R. M., Shanmugam, K., ve Dinstein, I., “Texture Features for Image Classification”, IEEE Trans. System Man Cybernat., 8 (6), 610–621, 1973.
11. Weszka, J. S., Dyer, C. R., ve Rosenfeld, A., “A Comparative Study of Texture Measures for Terrain Classification”, IEEE Trans. System Man Cybernat. SMC-6, (4), 269–286, 1976.
12. Davis, L. S., Johns, S. A., ve Aggarwal, J. K.,“Texture Analysis Using Generalized Co-Occurrence Matrices”, IEEE Trans. Pattern Anal. Machine Intell. PAMI-1, 251–259, 1979.
13. Faugeras, O. D., ve Pratt, W. K., “Decorrelation Methods of Texture Feature Extraction”, IEEE Trans. Pattern Anal. Machine Intell. PAMI-1,323–332, 1980.
14. Chen, P., C., ve Pavlidis, T., “Segmentation by Texture Using Correlation”, IEEE Trans. Pattern Anal. Machine Intell. PAMI-5, 64–69, 1983.
15. Cross, G., R., ve Jain, A., K., “Markov Random Field Texture Models”, IEEE Trans. Pattern Anal. Machine Intell. PAMI-5, (1), 25–39, 1983.
16. Kashyap, R. L., ve Khotanzed, A., “A Model Based Method for Rotation Invariant Texture Classification”, IEEE Trans. Pattern Anal. Machine Intell. PAMI-8, (4), 472–481, 1986.
17. Chellappa, R., ve Chatterjee, S., “Classification of textures using Gaussian Markov Random Fields”, IEEE Trans. Acoustics Speech Signal Process. ASSP-33, (4), 959–963, 1986.
18. Derin, H., ve Elliot, H., “Modeling and Segmenta tion of Noisy and Textured Images Using Gibbs Random Fields”, IEEE Trans. Pattern Anal. Machine Intell. PAMI-9, 39–59, 1987.
19. Cohen, F., S., Fan, Z., ve Patel, M., A., “Classification of Rotation and Scaled Textured Images Using Gaussian Markov Random Field Models”, IEEE Trans. Pattern Anal. Machine Intell., 13 (2),192–202, 1991.
20. Manjunath, B., S., ve Chellappa, R., “Unsupervised Texture Segmentation Using Markov Random Fields”, IEEE Trans. Pattern Anal. Machine Intell., 13, 478–482, 1991.
21. Laws, K. L., “Rapid Texture Identification”, Proc. SPIE, 238, 376–380, 1980.
22. Unser, M., “Local Linear Transforms for Texture Measurements”, Signal Process., 11, 61–79, 1986.
23. http://www.ux.his.no/~tranden/brodatz.html , 2005.
24. Avci, E., ve Turkoglu, I., “Modelling of Tunnel Diode by Adaptive-Network-Based Fuzzy Inference System”, Int. J. of Computational Intelligence,Cilt:1, No:1, 231-233, Temmuz, 2003.
25. Avci, E., Turkoglu, I., ve Poyraz, M., “Intelligent Target Recognition Based on Wavelet Packet Neural Network”, Experts Systems with Applications, 29(1), 2005.
26. Avci, E., Turkoglu, I., ve Poyraz, M., “A New Approach Based on Scalogram for Automatic Target Recognition with X-Band Doppler Radar”,Asian Journal of Information Technology, Cilt:4(1), 133-140, Ocak, 2005.
27. Avci, E., Turkoglu, I., ve Poyraz, M., “Intelligent Target Recognition Based on Wavelet Adaptive Network Based Fuzzy Inference System”, Lecture Notes in Computer Science, Springer-Verlag,Cilt: 3522 / 2005, 594-601, Mayıs, 2005.
28. Turkoglu, I., Arslan, A., ve Ilkay, E., “An Intelligent System for Diagnosis of the Heart Valve Diseases with Wavelet Packet Neaural Networks”, Computer in Biology and Medicine 33, 319-331, 2003.