A New Approach Based On FODPSO for Segmentation and Classification of Hyperspectral Image
|International Journal of Engineering Trends and Technology (IJETT)||
|© 2017 by IJETT Journal|
|Year of Publication : 2017|
|Authors : E.Venkatesh, Smt.S.Swarna Latha
|DOI : 10.14445/22315381/IJETT-V43P258|
E.Venkatesh, Smt.S.Swarna Latha " A New Approach Based On FODPSO for Segmentation and Classification of Hyperspectral Image ", International Journal of Engineering Trends and Technology (IJETT), V43(6),347-352 January 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group
Hyperspectral remote sensing images contain hundreds of data channels. Due to the high dimensionality of the hyperspectral data, it is difficult to design accurate and efficient image segmentation algorithms for such imagery. Here we introduce a novel algorithm for the segmentation of hyperspectral and multispectral images. This algorithm is based on fractional-order Darwinian particle swarm optimization (FODPSO) which exploits many swarms of test solutions that may exist at any time using Genetic Algorithm(GA). The Genetic Algorithm efficiently locate the global maximum in a search space and solves the problem of parameter selection in image segmentation .In addition to this a 2D adaptive log filter is proposed to denoise the hyperspectral image in order to remove the speckle noise and an adaptive Histogram coherence enhancement technique is used to improve the quality of the hyperspectral image. Here FCM is used to increase the clustering speed. Furthermore, the proposed clustering approach is combined with SVM classification to accurately classify hyperspectral images. The experimental results reveal that our proposed method is better compare to the state-of-art of criteria.
 R. Duda, P. Hart, and D. Stork, Pattern Classification, 2nd ed. Hoboken, NJ, USA: Wiley, 2001.
 A. Dutta, “Fuzzy c-means classification of multispectral data incorporatingspatial contextual information by using Markov random field,” M.S. thesis, Geo informatics, ITC, 2009.
 J. Bezdek, Fuzzy Mathematics in Pattern Classification, 2nd ed. Hoboken,NJ, USA: Wiley, 1973.
 W. Wang, Y. Zhang, Y. Li, and X. Zhang, “The global fuzzy c-meansclustering algorithm,” inIntelligent Control and Automation, vol. 1,pp. 3604–3607, 2006.
 J. Kennedy and R. Eberhart, “A new optimizer using particle swarm theory,”in Proc. IEEE 6th Int. Symp. Micro Mach. Hum. Sci., 1995, vol. 34,no. 2008, pp. 39–43.
 M. S. Couceiro, R. P. Rocha, N. M. F. Ferreira, and J. A. T. Machado,“Introducing the fractional order darwinian PSO,” Signal Image VideoProcess., vol. 102, no. 1, pp. 8–16, 2007.
 P. Ghamisi, M. S. Couceiro, J. A. Benediktsson, and N. M. F. Ferreira,“An efficient method for segmentation of images based on fractional calculus and natural selection,” Expert Syst. Appl., vol. 39, no. 16, pp. 12407–12 417, 2012.
 P. Ghamisi, M. S. Couceiro, F. M. Martins, and J. A. Benediktsson, “Multilevel image segmentation approach for remote sensing images based on fractional-order Darwinian particle swarm optimization,” IEEETrans. Remote Sens. Geosci., vol. 52, no. 5, pp. 2382–2394, May 2014.
 P. Ghamisi,M. Couceiro, M. Fauvel, and J. A. Benediktsson, “Integration of segmentation techniques for classification of hyperspectral images, ”IEEE Geosci. Remote Sens. Lett., vol. 11, no. 1, pp. 342–346, Jan. 2014.
 P. Ghamisi, M. S. Couceiro, and J. A. Benediktsson, “Classification of hyperspectral images with binary fractional order darwinian PSO and random forests,” Proc. SPIE, vol. 8892, pp. 88 920S–88 920S-8, 2013.
FODPSO,2D adaptive log filter, FCM, SVM ,Genetic Algorithm.