(43-2) 14 * << * >> * Русский * English * Содержание * Все выпуски

 PDF, 995 kB

DOI: 10.18287/2412-6179-2019-43-2-264-269

Страницы: 264-269.

Аннотация:
In the field of color texture segmentation, region-level Markov random field model (RMRF) has become a focal problem because of its efficiency in modeling the large-range spatial constraints. However, the RMRF defined on a single scale cannot describe the un-stationary essence of the image, which highly limits its robustness. Hence, by combining wavelet transformation and the RMRF model, we present a multi-scale RMRF (MsRMRF) model in wavelet domainin this paper. In the Bayesian framework, the proposed model seamlessly integrates the multi-scale information stemmed from both the original image and the region-level spatial constraints. Therefore, the new model can accurately describe the characteristics of different kinds of texture. Based on MsRMRF, an unsupervised segmentation algorithm is designed for segmenting color texture images. Both synthetic color texture images and remote sensing images are employed in the comparative experiments, and the experimental results show that the proposed method can obtain more accurate segmentation results than the competitors.

Ключевые слова:
region-level Markov random field model, color texture image, image segmentation, wavelet transformation, multi-scale.

Цитирование:
Song X, Wu L, Liu G. Unsupervised color texture segmentation based on multi-scale region-level Markov random field models. Computer Optics 2019; 43(2): 264-269. DOI: 10.18287/2412-6179-2019-43-2-264-269.

1. Drira, F. Mean-Shift segmentation and PDE-based nonlinear diffusion: toward a common variational framework for foreground/background document image segmentation / F. Drira, F. Lebourgeois // International Journal on Document Analysis & Recognition. – 2017. – Vol. 20, Issue 3. – P. 1-22.
2. Kim, T.H. Learning full pairwise affinities for spectral segmentation / T.H. Kim, K.M. Lee, U.L. Sang // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2013. – Vol. 35, Issue 7. – P. 1690-1703.
3. Abdelsamea, M. A SOM-based Chan–Vese model for unsupervised image segmentation / M. Abdelsamea, G. Gnecco, M. Gaber // Soft Computing. – 2017. – Vol. 21, Issue 8. – P. 1-21.
4. Krinidis, S. A robust fuzzy local information C-Means clustering algorithm / S. Krinidis, V. Chatzis // IEEE Transactions on Image Processing. – 2010. – Vol. 19, Issue 5. – P. 1328-1337.
5. Gong, M. Fuzzy C-means clustering with local information and kernel metric for image segmentation / M. Gong, Y. Liang, J. Shi, W. Ma, J. Ma // IEEE Transactions on Image Processing. – 2013. – Vol. 22, Issue 2. – P. 573-584.
6. Zhang, H. Effective fuzzy clustering algorithm with Bayesian model and mean template for image segmentation / H. Zhang, Q.M.J. Wu, Y. Zheng, T.M. Nguyen, D. Wang // IET Image Processing. – 2014. – Vol. 8, Issue 10. – P. 571-581.
7. Yu, Q. IRGS: image segmentation using edge penalties and region growing / Q. Yu, D.A. Clausi // IEEE Transactions on Pattern Analysis & Machine Intelligence 2008, 30(12): 2126-2139.
8. Chatzis, S.P. A fuzzy clustering approach toward hidden Markov random field models for enhanced spatially constrained image segmentation / S.P. Chatzis, T.A. Varvarigou // IEEE Transactions on Fuzzy Systems. – 2008. – Vol. 16, Issue 5. – P. 1351-1361.
9. Liu, G.-Y. Fuzzy clustering algorithm for integrating multiscale spatial context in image segmentation by hidden markov random field models / G.-Y. Liu, A.-M. Wang // International Journal of Pattern Recognition and Artificial Intelligence. – 2013. – Vol. 27, Issue 3. – 1355005.
10. Liu, G. Incorporating adaptive local information into fuzzy clustering for image segmentation / G. Liu, Y. Zhang, A. Wang // IEEE Transactions on Image Processing. – 2015. – Vol. 24, Issue 11. – P. 3990-4000.
11. Qin, A.K. Multivariate image segmentation using semantic region growing with adaptive edge penalty / A.K. Qin, D.A. Clausi // IEEE Transactions on Image Processing. – 2010. – Vol. 19, Issue 8. – P. 2157-2170.
12. Yang, F. Pixon-based image segmentation with Markov random fields / F. Yang, T. Jiang // IEEE Transactions on Image Processing. – 2003. – Vol. 12, Issue 12. – P. 1552-1559.
13. Besag, J. On the statistical analysis of dirty pictures / J. Besag // Journal of the Royal Statistical Society. – 1986. – Vol. 48, Issue 3. – P. 259-302.
14. Zhang, Y. Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm / Y. Zhang, M. Brady, S. Smith // IEEE Transactions on Medical Imaging. – 2001. – Vol. 20, Issue 1. – P. 45-57.
15. Xia, G.-S. Integration of synthetic aperture radar image segmentation method using Markov random field on region adjacency graph / G.-S. Xia, C. He, H. Sun // IET Radar, Sonar and Navigation 2007, 1(5): 348-353.
16. Boykov, Y. Graph cuts and efficient N-D image segmentation / Y. Boykov, G. Funkalea // International Journal of Computer Vision. – 2006. – Vol. 70, Issue 2. – P. 109-131.
17. Liu, G. A multispectral textured image segmentation method based on MRMRF / G. Liu, L. Luo, T. Mei, Q. Qin // Geomatics and Information Science of Wuhan University. – 2008. – Vol. 33, Issue 9. – P. 963-966.
18. Lin, L. A novel pixon-representation for image segmentation based on Markov random field / L. Lin, L. Zhu, F. Yang, T. Jiang // Image and Vision Computing. – 2008. – Vol. 26, Issue 11. – P. 1507-1514.
19. The Prague texture segmentation datagenerator and benchmark – Introductory page. – URL: mosaic.utia.cas.cz/ (requets date 06.12.2018).

---

© 2009, IPSI RAS
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: journal@computeroptics.ru ; тел: +7 (846) 242-41-24 (ответственный секретарь), +7 (846) 332-56-22 (технический редактор), факс: +7 (846) 332-56-20