logo

SCIENTIA SINICA Informationis, Volume 47, Issue 1: 86-98(2017) https://doi.org/10.1360/N112016-00016

Energy cut based SAR image segmentation}{Energy cut based SAR image segmentation

More info
  • ReceivedJan 19, 2016
  • AcceptedFeb 26, 2016
  • PublishedOct 25, 2016

Abstract

This paper presents a novel graph partitioning criterion, energy cut, for SAR image segmentation, based on the law of universal gravitation. The main characteristic of the energy cut is that its optimization can produce graph partitioning with minimal inter-cluster and maximal intra-cluster gravitation. We show that the optimal continuous approximation solution to the energy cut can be obtained by solving an eigenvector problem. Furthermore, we also present a simple discretization method to derive the optimal discrete approximation solution. The experimental results on the synthesized and real-world SAR images are very encouraging, demonstrating the effectiveness of the new criterion.


References

[1] Smith D M. Speckle reduction and segmentation of synthetic aperture radar images. Int J Remote Sens, 1996, 17: 2043-2057 CrossRef Google Scholar

[2] Roger F, Armand L, Philippe M, et al. An optimal multiedge detector for SAR mage segmentation. IEEE Trans Geosci Remote Sens, 1998, 36: 793-802 CrossRef Google Scholar

[3] Carvalho E A, Ushizima D M, Medeiros F N S, et al. SAR imagery segmentation by statistical region growing and hierarchical merging. Digital Signal Process, 2010, 20: 1365-1378 CrossRef Google Scholar

[4] Huawu D, Clausi D A. Unsupervised segmentation of synthetic aperture radar sea ice imagery using a novel markov random field model. IEEE Trans Geosci Remote Sens, 2005, 43: 528-538 CrossRef Google Scholar

[5] Yu P, Qin A K, Clausi D A. Unsupervised polarimetric SAR image segmentation and classification using region growing with edge penalty. IEEE Trans Geosci Sens, 2012, 50: 1302-1317 CrossRef Google Scholar

[6] Marques R C P, Medeiros F N, Nobre J S. SAR image segmentation based on level set approach and model. IEEE Trans Pattern Anal Mach Intell, 2012, 34: 2046-2057 CrossRef Google Scholar

[7] Oliver C, Quegan S. Understanding Synthetic Aperture Radar Images. Raleigh: SciTech Publishing Inc, 2004. 195-257. Google Scholar

[8] Caves R, Quegan S, White R. Quantitative comparison of the performance of SAR segmentation algorithms. IEEE Trans Image Process, 1998, 7: 1534-1546 CrossRef Google Scholar

[9] Tung F, Wong A, Clausi D. Enabling scalable spectral clustering for image segmentation. Pattern Recogn, 2010, 43: 4069-4076 CrossRef Google Scholar

[10] Garc\'{\i}a J F G, Venegas-Andraca S E. Region-based approach for the spectral clustering Nyström approximation with an application to burn depth assessment. Mach Vision Appl, 2015, 26: 353-368 CrossRef Google Scholar

[11] Jiang M, Li C, Feng J, et al. Segmentation via ncuts and lossy minimum description length: a unified approach. In: Proceedings of the 10th Asian Conference on Computer Vision. Berlin: Springer, 2011. 213-224. Google Scholar

[12] Li X, Tian Z. Multiscale stochastic hierarchical image segmentation by spectral clustering. Sci China Ser F-Inf Sci, 2007, 50: 198-211 CrossRef Google Scholar

[13] Kuo C T, Walker P B, Carmichael O, et al. Spectral Clustering for Medical Imaging. In: Proceedings of IEEE International Conference on Data Mining, Shenzhen, 2014. 887-892. Google Scholar

[14] Rezvanifar A, Khosravifard M. Including the size of regions in image segmentation by region-based graph. IEEE Trans Image Process, 2014, 23: 635-644 CrossRef Google Scholar

[15] Gou S P, Zhuang X, Jiao L C. Quantum immune fast spectral clustering for SAR image segmentation. IEEE Geosci Remote Sens Lett, 2012, 9: 8-7 CrossRef Google Scholar

[16] Ersahin K, Cumming I G, Ward R K. Segmentation and classification of polarimetric SAR data using spectral graph partitioning. IEEE Trans Geosci Remote Sens, 2010, 48: 164-174 CrossRef Google Scholar

[17] Rahmani M, Akbarizadeh G. Unsupervised feature learning based on sparse coding and spectral clustering for segmentation of synthetic aperture radar images. IET Comput Vision, 2015, 9: 629-638 CrossRef Google Scholar

[18] Shi J, Malik J. Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell, 2000, 22: 888-905 CrossRef Google Scholar

[19] Hagen L, Kahng A B. New spectral methods for ratio cut partitioning and clustering. IEEE Trans Comput Aided Design, 1992, 11: 1074-1085 CrossRef Google Scholar

[20] Ding C H Q, He X, Zha H, et al. A min-max cut algorithm for graph partitioning and data clustering. In: Proceedings of IEEE International Conference on Data Mining, San Jose, 2001. 107-114. Google Scholar

[21] von Luxburg U. A Tutorial on Spectral Clustering. Max Planck Institute for Biological Cybernetics. Technical Report TR-149. 2006. Google Scholar

[22] Nascimento M C V, de Carvalho A C P L F. Spectral methods for graph clustering--a survey. Eur J Oper Res, 2011, 211: 221-231 CrossRef Google Scholar

[23] Fowlkes C, Belongie S, Chung F, et al. Spectral grouping using the Nyström method. IEEE Trans Pattern Anal Mach Intell, 2004, 26: 214-225 CrossRef Google Scholar

[24] Ng A Y, Jordan M I, Weiss Y. On spectral clustering: analysis and an algorithm. In: Dietterich T G, Becker S, Ghahramani Z, eds. Advances in Neural Information Processing Systems 14. Cambridge: MIT Press, 2002. 849-856. Google Scholar

[25] Yu S X, Shi J. Multiclass spectral clustering. In: Proceedings of the 9th IEEE International Conference on Computer Vision, Nice, 2003. 313-319. Google Scholar

[26] Xiang T, Gong S. Spectral clustering with eigenvector selection. Pattern Recogn, 2008, 41: 1012-1029 CrossRef Google Scholar

[27] Sun J G. Matrix Perturbation Analysis. 2nd ed. Beijing: Science Press, 2001. 60-71 [孙继广. 矩阵的扰动分析. 第2版. 北京: 科学出版社, 2001. 60-71]. Google Scholar

Copyright 2019 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1