SAR image segmentation using MSER and improved spectral clustering
Tóm tắt
A novel approach is presented for synthetic aperture radar (SAR) image segmentation. By incorporating the advantages of maximally stable extremal regions (MSER) algorithm and spectral clustering (SC) method, the proposed approach provides effective and robust segmentation. First, the input image is transformed from a pixel-based to a region-based model by using the MSER algorithm. The input image after MSER procedure is composed of some disjoint regions. Then the regions are treated as nodes in the image plane, and a graph structure is applied to represent them. Finally, the improved SC is used to perform globally optimal clustering, by which the result of image segmentation can be generated. To avoid some incorrect partitioning when considering each region as one graph node, we assign different numbers of nodes to represent the regions according to area ratios among the regions. In addition, K-harmonic means instead of K-means is applied in the improved SC procedure in order to raise its stability and performance. Experimental results show that the proposed approach is effective on SAR image segmentation and has the advantage of calculating quickly.
Tài liệu tham khảo
Kersten PR, Lee JS, Ainsworth TL: Unsupervised classification of polarimetric synthetic aperture radar images using fuzzy clustering and EM clustering. IEEE Trans Geosci Remote Sens 2005, 43(3):519-527.
Zarrt AE, Ziou D, Wang S, Jiang Q: Segmentation of SAR images. Pattern Recogn 2002, 35(3):713-724.
Lee JS, Jurkevich I: Segmentation of SAR images. IEEE Trans Geosci Remote Sens 1989, 27(6):674-680.
Ogor B, Haese-coat V, Ronsin J: SAR image segmentation by mathematical morphology and texture analysis. In Proceedings Int Geoscience and Remote Sensing Symposium. Volume 1. Lincoln, Nebraska, USA; 1996:717-719.
Ma XL, Jiao LC: SAR image segmentation based on watershed and spectral clustering. J Infared Millim Waves 2008, 27(6):452-457.
Zhang XR, Jiao LC, Liu F, Bo LF, Gong MG: Spectral clustering ensemble applied to SAR image segmentation. IEEE Trans Geosci Remote Sens 2008, 46(7):2126-2135.
Deng H, Clausi DA: Unsupervised segmentation of synthetic aperture radar sea ice imagery using a novel Markov random field model. IEEE Trans Geosci Remote Sens 2005, 43(3):528-538.
Dong Y, Forster BC, Milne AK: Comparison of radar image segmentation by Gaussian- and Gamma-Markov random field models. Int J Remote Sens 2003, 24(4):711-722.
Shi J, Malik J: Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 2000, 22(8):888-905.
Ng AY, Jordan MI, Weiss Y: On spectral clustering: analysis and an algorithm. Adv Neural Inf Process Syst 2001, 14(14):849-856.
Matas J, Chun O, Urban M, Pajdla T: Robust wide baseline stereo from maximally stable extremal regions. In Proceedings of British Machine Vision Conference. Volume 1. Cardiff, UK; 2002:384-394.
Mikolajczyk K, Schmid C: A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 2005, 27(10):1615-1630.
Bosch A, Zisserman A, Munoz X: Scene classification via pLSA. In Proceedings of European Conference on Computer Vision. Volume 4. Graz, Austria; 2006:517-530.
Sivic J, Zisserman A: Video Google: a text retrieval approach to object matching in videos. In Proceedings of International Conference on Computer Vision. Volume 2. Nice, France; 2003:1470-1477.
He XF, Cai D, Wen JR, Ma WY, Zhang HJ: Clustering and searching WWW images using link and page layout analysis. ACM Trans Multimedia Comput Commun Appl 2007., 3(2): Article 10, doi:10.1145/1230812.1230816
Higham DJ, Kalna G, Kibble M: Spectral clustering and its use in bioinformatics. J Comput Appl Math 2007, 204(1):25-37.
Cour T, Benezit F, Shi J: Spectral segmentation with multi-scale graph decomposition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Volume 2. San Diego, USA; 2005:1124-1131.
Tao WB, Jin H: Ship infrared object segmentation based on meanshift filitering and graph spectral clustering. J Infrared Millim Waves 2007, 26(1):61-64.
Archip N, Rohling R, Cooperberg P, Tahmasebpour H, Warfield SK: Spectral clustering algorithms for ultrasound image segmentation. Medical Image Computing and Computer-assisted in Intervention, Lecture notes in Computer Science 2005, 3750: 862-869.
O'Callaghan RJ, Bull DR: Combined morphological-spectral unsupervised image segmentation. IEEE Trans Image Process 2005, 14(1):49-62.
Fowlkes C, Belongie S, Chung F, Malik J: Spectral grouping using the Nystrom method. IEEE Trans Pattern Anal Mach Intell 2004, 26(2):214-225.
Tao WB, Jin H, Zhang YM: Color Image Segmentation Based on Mean shift and Normalized Cuts. IEEE Trans Syst ManCybern Part B: Cybern 2007, 37(5):1382-1389.
Boykov Y, Kolmogorov V: An experiment comparison of min-cut/max-flow algorithm for energy minimization in vision. IEEE Trans PAMI 2004, 26(9):1124-1137.
Boykov Y, Veksler O, Zabih R: Fast approximate energy minimization via Graph Cuts. IEEE Trans PAMI 2004, 23(11):1222-1239.
Zhang B: Generalized K-Harmonic means - dynamic weighting of data in unsupervised learning. In the First SIAM International Conference on Data Mining. Chicago, USA; 2001.
Zhang B, Hsu M, Dayal U: K-Harmonic means: a spatial clustering algorithm with boosting. Proceedings of the First Workshop on Temporal, Spatial, and Spatio-Temporal Data Mining-Revised Papers table of contents, Lecture notes in Computer Science 2001, 2007: 31-45.
Li Q, Mitianoudis N, Stathaki T: Spatial kernel K-Harmonic means clustering for multi-spectral image segmentation. IEEE Trans Image Process 2006, 1(2):156-167.
Kristensen F, MacLean WJ: Real-time extraction of maximally stable extremal regions on an FPGA. In IEEE International Symposium on Circuits and Systems. Orleans, Louisiana, USA; 2007:165-168.
Nister D, Stewenius H: Linear time maximally stable extremal regions. In Proceedings of European Conference on Computer Vision. Volume 5303. Marseille, France; 2008:183-196.
Meila M, Shi JB: A random walks view of spectral segmentation. AI Stat 2001, 2001: 8-11.
Luxburg UV, Bousquet O: Limits of spectral clustering. Adv Neural Inf Process Syst 2005, 17: 857-864.
Sandia National Laboratories[http://www.sandia.gov/radar/imagery.html]
Cour T, Yu S, Shi J: Normalized cuts matlab code.[http://www.cis.upenn.edu/~jshi/software]