Mixture model and Markov random field-based remote sensing image unsupervised clustering method

• Autorzy: Hou Y. , Yang Y. , Rao N. , Lun X. , Lan J.
• Języki publikacji: EN

Abstrakty

EN

In this paper, a novel method for remote sensing image clustering based on mixture model and Markov random field (MRF) is proposed. A remote sensing image can be considered as Gaussian mixture model. The image clustering result corresponding to the image label field is a MRF. So, the image clustering procedure is transformed to a maximum a posterior (MAP) problem by Bayesian theorem. The intensity difference and the spatial distance between the two pixels in the same clique are introduced into the traditional MRF potential function. The iterative conditional model (ICM) is employed to find the solution of MAP. We use the max entropy criterion to choose the optimal clustering number. In the experiments, the method is compared with the traditional MRF clustering method using ICM and simulated annealing (SA). The results show that this method is better than the traditional MRF model both in noise filtering and miss-classification ratio.

Słowa kluczowe

EN

remote sensing image; Markov random field; maximum a posteriori; iterative conditional model

• Wydawca: Stowarzyszenie Elektryków Polskich ; Polska Akademia Nauk ; Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Opto-Electronics Review
• Rocznik: 2011
• Tom: Vol. 19, No. 1
• Strony: 83--88
• Opis fizyczny: Bibliogr. 23 poz., il., wykr.

Twórcy

autor

Hou Y.

autor

Yang Y.

autor

Rao N.

autor

Lun X.

autor

Lan J.

• School of Automation Engineering, Northeast Dianli University, 132012 Jilin, China,

Bibliografia

• [1] G. Noyel, J. Angulo, and D. Jeulin: Random germs and stochastic watershed for unsupervised multispectral image segmentation. Proc. 10 th Int. Conf. on Knowledge-Based & Intelligent Information & Engineering Systems, Bournemouth, 17-24, 2006.
• [2] L. Wang, W. Wu, Q. Dai, and Q. Qin: Remote sensing image texture classification based on Gabor wavelet and support vector machine. Geoinformatics (China) 6419, 413-419, 2006.
• [3] C. R. Jung: Unsupervised multiscale segmentation of colour images. Pattern Recogn. Lett. 28, 523-533, 2007.
• [4] U. C. Benz, P. Hofman, G. Willhauck, I. Lingenfelder, and M. Heynen: Multi-resolusion object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J. Photogramm. 58, 239-258, 2004.
• [5] F. Forbes and G. Fort: Combining Monte Carlo and mean-field-like methods for inference in hidden Markov random fields. IEEE T. Image Process. 16, 824-837, 2007.
• [6] R. Nishii and S. Eguchi: Supervised image classification by contextual AdaBoost based on posteriors in neighbourhoods. IEEE T. Geosci. Remote 43, 2547-2554, 2005.
• [7] F. Destrempes, M. Mignotte, and J. F. Angers: A stochastic method for Bayesian estimation of hidden Markov random field models with application to a colour model. IEEE T. Image Process. 14, 1096-1108, 2005.
• [8] J. Wu and C. S. Albert: A segmentation model using compound Markov random fields based on a boundary model. IEEE T. Image Process. 16, 241-252, 2007.
• [9] X. Liu, D. L. Langer, M. A. Haider, Y. Yang, M. N. Wernick, and I. S. Yetik: Prostate cancer segmentation with simultaneous estimation of Markov random field parameters and class. IEEE T. Med. Imaging 28, 906-915, 2009.
• [10] X. F. Wang and X. P. Zhang: A new localized superpixel Markov random field for image segmentation. IEEE Int. Conf. on Multimedia & Expo (ICME 2009), Mexico, 642-645, 2009.
• [11] B. Fischer and J. M. Buhmann: Path-based clustering for grouping of smooth curves and texture segmentation. IEEE T. Pattern Anal. 25, 513-518, 2003.
• [12] A. Topchy, A. K. Jain, and W. Punch: Combining multiple weak clustering. in Proc. IEEE Int. Conf. on Data Mining, Melbourne, FL, 331-338, 2003.
• [13] A. Strehl and J. Ghosh: Cluster ensembles-acknowledge reuse framework for combining multiple partitions. J. Mach. Learn. Res. 3, 583-617, 2002.
• [14] T. Lei and J. Udupa: Performance evaluation of finite normal mixture model-based image segmentation techniques. IEEE T. Image Process. 12, 1153-1169, 2003.
• [15] B. Zadrozny and C. Elkan: Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers. Proc. 18 th Int. Conf. on Machine Learning, Morgan Kaufmann, San Francisco, CA, 609-616, 2001.
• [16] A. Vetro, Y. Wang, and H. Sun: Rate-distortion modelling for multiscale binary shape coding based on Markov random fields. IEEE T. Image Process. 12, 356-364, 2003.
• [17] B. C. K. Tso and P. M. Mather: Classification of multisource remote sensing imagery using a genetic algorithm and Markov random fields. IEEE T. Geosci. Remote 37, 1255-1260, 1999.
• [18] M. A. Hurn, K. V. Mardia, T. J. Hainsworth, J. Kirkbride, and E. Berry: Bayesian fused classification of medical images. IEEE T. Med. Imaging 15, 850-858, 1996.
• [19] X. Jia and J. A. Richards: Managing the spectral-spatial mix in context classification using Markov random fields. IEEE Geosci. Remote S. 5, 311-314, 2008.
• [20] J. M. Laferté, P. Perez, and F. Heitz: Discrete Markov image modelling and inference on the quadtree. IEEE T. Image Process. 9, 390-404, 2000.
• [21] V. A. Tolpekin and N. A. S. Hamm: Fuzzy super resolution mapping based on Markov random fields. IEEE Geosci. Remote Sensing Symp., Boston, 875-878, 2008.
• [22] D. W. Kim, K. H. Lee, and D. Lee: On cluster validity index for estimation of the optimal number of fuzzy clusters. Pattern Recogn. 37, 2009-2025, 2004.
• [23] J. C. Bezdek and R. Hathaway: Convergence theory for fuzzy C-Means: Counter examples and repairs [J]. IEEE T. Syst. Man Cyb. 17, 873-877, 1987.