Because of the multiplicative nature of the speckle noise in SAR images, it is difficult to solve SAR image segmentation problems using general image segmentation technique. A novel SAR image segmentation algorithm based on an artificial immune system is proposed. After extracting texture features from an image and encoding them with real numbers, it determines partitioning of the feature vectors by optimizing the objective function based on clonal operator. The experimental results show that the novel algorithm is feasible and effective for SAR image segmentation.
Oliver C and Quegan S. Understanding Synthetic ApertureRadar Images [M]. Norwood: Artech House Inc, 1998: 88-204.[2]Dammert P B G, Asken J I H, and Kuhlmann S.Unsupervised segmentation of multitemporal interferomentricSAR images[J].IEEE Transactions on Geoscience and RemoteSensing.1999, 37(9):2259-2271[3]Dekker R J. Texture analysis and classification of ERS SARimages for map updating of urban areas in the Netherland[J].IEEE Transactions on Geoscience and Remote Sensing.2003,41(9):1950-1958[4]Kersten P R, Lee Jong-Sen, and Ainsworth T L.Unsupervised classification of polarimentric SyntheticAperture Radar images using fuzzy clustering and EMclustering[J].IEEE Transactions on Geoscience and RemoteSensing.2005, 43(3):519-527[5]Maulik U and Bandyopadhyay S. Genetic algorithm-basedclustering technique[J].Pattern Recognition.2000, 33(9):1455-1465[6]Gong Mao-guo, Du Hai-feng, and Jiao Li-cheng. Optimalapproximation of linear systems by artificial immuneresponse[J].Science in China Series F-Information Sciences.2006, 49(1):63-79[7]Jain A K, Murty M N, and Flynn P J. Data, clustering: Areview[J].ACM Computing Surveys.1993, 31(3):264-323[8]Pan H, Zhu J, and Han D. Genetic algorithms applied tomulticlass clustering for gene expression data[J].Genomics,Proteomics Bioinformatics.2003, 1(4):279-287[9]Hall L O, Ozyurt I B, and Bezdek J C. Clustering with agenetically optimized approach[J].IEEE Transactions onEvolutionary Computation.1999, 3(2):103-112[10]Clausi D A and Yue B. Comparing CooccurrenceProbabilities and Markov random fields for texture analysisof SAR sea ice imagery[J].IEEE Transactions on Geoscienceand Remote Sensing.2004, 42(1):215-228