Multispectral remote sensing image segmentation using rival penalized controlled competitive learning and fuzzy entropy
Tóm tắt
This paper proposes an image segmentation approach for multispectral remote sensing imagery based on rival penalized controlled competitive learning (RPCCL) and fuzzy entropy. In this approach, the clustering center component for each band of the image is first chosen based on the fuzzy entropy histogram of the corresponding band of the image. The initial clustering centers are then formed by combining the obtained clustering center components. The number of clusters and the real clustering centers are then determined by the use of the RPCCL method. The advantages of the proposed approach are the appropriate initial cluster centers and the fact that the number of clusters is determined automatically. The results of the experiments showed that without providing the number of clustering centers before the clustering operation, the proposed method can effectively perform an unsupervised segmentation of remote sensing images.
Tài liệu tham khảo
Aguilar MA, Saldana MM, Aguilar FJ (2013) GeoEye-1 and WorldView-2 pan-sharpened imagery for object-based classification in urban environments. Int J Remote Sens 34(7):2583–2606. doi:10.1080/01431161.2012.747018
Ahalt SC, Krishnamurty AK, Chen P (1990) Competitive learning algorithms for vector quantization. IEEE Trans Neural Netw 3(3):277–291. doi:10.1016/0893-6080(90)90071-R
Ball G, Hall D (1967) A clustering technique for summarizing multivariate data. Behav Sci 12:153–155. doi:10.1002/bs.3830120210
Bensaid AM, Hall LO, Bezdek JC, Clarke Laurence P, Silbiger ML, Arrington JA, Murtagh RF (1996) Validity-guided (re)clustering with applications to image segmentation. IEEE Trans Fuzzy Syst 4(2):112–123. doi:10.1109/91.493905
Bilgin G, Erturk S, Yildirim T (2011) Segmentation of hyperspectral images via subtractive clustering and cluster validation using one-class support vector machines. IEEE Trans Geosci Remote Sens 49(8):2936–2944. doi:10.1109/TGRS.2011.2113186
Chen Q (2005) An improved RPCCL approach and its application to segmentations of remotely sensed imagery. Comput Eng Appl 34:221–223 (in Chinese)
Cheng HD, Jiang XH, Sun Y, Wang JL (2001) Color image segmentation: advances and prospects. Pattern Recogn 34:2259–2281. doi:10.1016/S0031-3203(00)00149-7
Cheng HD, Jiang XH, Wang JL (2002) Color image segmentation based on homogram thresholding and region merging. Pattern Recogn 35(2):373–393. doi:10.1016/S0031-3203(01)00054-1
Cheng HD, Li J (2003) Fuzzy homogeneity and scale-space approach to color image segmentation. Pattern Recogn 36(7):1545–1562. doi:10.1016/S0031-3203(02)00293-5
Chen S, Mei T, Luo M, Liang H (2007) Study on a new RPCCL clustering algorithm. In: Proceedings of international conference mechatronics automation, Harbin, China, Aug 5–8, 2007, pp 299–303. doi:10.1109/ICMA.2007.4303558
Cheung Y (2002), Rival penalization controlled competitive learning for data clustering with unknown cluster number, neural information processing, 2002, ICONIP ’02. In: Proceedings of the 9th international conference, vol 1, pp. 18–22. doi:10.1109/ICONIP.2002.1202214
Cheung Y (2005) On rival penalization controlled competitive learning for clustering with automatic cluster number selection. IEEE Trans Knowl Data Eng 17(11):1583–1588. doi:10.1109/TKDE.2005.184
Das S, Mirnalinee TT, Varghese K (2011) Use of salient features for the design of a multistage framework to extract roads from high-resolution multispectral satellite images. IEEE Trans Geosci Remote Sens 49(10):3906–3931. doi:10.1109/TGRS.2011.2136381
Fan J, Han M, Wang J (2009) Single point iterative weighted fuzzy C-means clustering algorithm for remote sensing image segmentation. Pattern Recogn 42(11):2527–2540. doi:10.1016/j.patcog.2009.04.013
Gomez D, Montero J (2008) Fuzzy sets in remote sensing classification. Soft Comput 12(3):243–249. doi:10.1007/s00500-007-0201-z
Halder A, Ghosh A, Ghosh S (2011) Supervised and unsupervised landuse map generation from remotely sensed images using ant based systems. Appl Soft Comput 11(8):5770–5781. doi:10.1016/j.asoc.2011.02.030
Hartigan JA, Wong MA (1979) Algorithm AS 136: a K-means clustering algorithm. J Roy Stat Soc C Appl Stat 28(1):100–108. doi:10.2307/2346830
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323. doi:10.1145/331499.331504
Li N, Huo H, Zhao Y, Chen X, Fang T (2013) A spatial clustering method with edge weighting for image segmentation. IEEE Geosci Remote S 10(5):1124–1128. doi:10.1109/LGRS.2012.2231662
Murthy CA, Pal SK (1992) Histogram thresholding by minimizing graylevel fuzziness. Inf Sci 60(1):107–135. doi:10.1016/0020-0255(92)90007-U
Pal SK, King RA, Hashim AA (1983) Automatic grey level thresholding through index of fuzziness and entropy. Pattern Recogn Lett 1(3):141–146. doi:10.1016/0167-8655(83)90053-3
Paoli A, Melgani F, Pasolli E (2009) Clustering of hyperspectral images based on multiobjective particle swarm optimization. IEEE Trans Geosci Remote Sens 47(12):4175–4188. doi:10.1109/TGRS.2009.2023666
Rumelhart D, Zipser D, McClelland JL, et al. (1986) Parallel distributed processing, vol 1. MIT Press, Cambridge, pp 151–193
Singh KK, Nigam MJ, Pal K, Mehrotra A (2014) A fuzzy kohonen local information C-means clustering for remote sensing imagery. IETE Tech Rev 31(1):75–81. doi:10.1080/02564602.2014.891375
Sziranyi T, Shadaydeh M (2014) Segmentation of remote sensing images using similarity-measure-based fusion-MRF mode. IEEE Trans Geosci Remote Sens 11(9):1544–1548. doi:10.1109/LGRS.2014.2300873
Trivedi MM, Bezdek JC (1986) Low-level segmentation of aerial images with fuzzy clustering. IEEE Trans Syst Man Cybern 16(4):589–598. doi:10.1109/TSMC.1986.289264
Tuia D, Muñoz-Marí J, Camps-Valls G (2012) Remote sensing image segmentation by active queries. Pattern Recogn 45(6):2180–2192. doi:10.1016/j.patcog.2011.12.012
Wallace CS, Boulton DM (1968) An information measure for classification. Comput J 11(2):185–194. doi:10.1093/comjnl/11.2.185
Xie ZX, Roberts C, Johnson B (2008) Object-based target search using remotely sensed data: A case study in detecting invasive exotic Australian Pine in south Florida. ISPRS J Photogramm Remote Sens 63(6):647–660. doi:10.1016/j.isprsjprs.2008.04.003
Xie H, Tong X (2014) A Probability-Based Improved Binary Encoding Algorithm for Classification of Hyperspectral Images. IEEE J Sel Topic Appl Earth Observ Remote Sens 7(6):2108–2118. doi:10.1109/JSTARS.2013.2273795
Xu L, Krzyzak A, Oja E (1993) Rival penalized competitive learning for clustering analysis, RBF net, and curve detection. IEEE Trans Neural Netw 4(4):636–649. doi:10.1109/72.238318
Zhong Y, Zhang S, Zhang L (2013) Automatic fuzzy clustering based on adaptive multi-objective differential evolution for remote sensing imagery. IEEE J Sel Topic Appl Earth Observ Remote Sens 6(5):1124–1128. doi:10.1109/JSTARS.2013.2240655
Zhong Y, Ma A, Zhang L (2014) An adaptive memetic fuzzy clustering algorithm with spatial information for remote sensing imagery. I IEEE J Sel Topic Appl Earth Observ Remote Sens 7(4):1235–1248. doi:10.1109/JSTARS.2014.2303634
Zhong Y, Zhao B, Zhang L (2014b) Multiagent object-based classifier for high spatial resolution imagery. IEEE Trans Geosci Remote Sens 52(2):841–857. doi:10.1109/TGRS.2013.2244604