Abstract Combined with neural network, a method for remote sensing image classification based on runlength features is proposed. According to the criterion of variances between and intra classes, the efficient features are selected and the redundant ones are excluded successfully by the method of rough set. Runlength features, cooccurrence features, gray levelgradient cooccurrence features and gray levelsmoothed cooccurrence features are respectively used as inputs of three types of classifiers: BP net, RBF net and a nearest neighbor classifier-KNN method, when applying remote sensing classification for large scale panchromatic SPOT images with high spatial resolution. The result demonstrates the efficiency of the proposed algorithm.
[1] Zhou Chenghu, Luo Jiancheng. Remote Sensing Comprehension and Analysis. Beijing, China: Science Press, 2003 (in Chinese) (周成虎,骆剑承.遥感影像地学理解与分析.北京:科学出版社, 2003) [2] Tang Xiaoou. Texture Information in RunLength Matrices. IEEE Trans on Image Processing, 1998, 7(11): 16021609 [3] Galloway M M. Texture Analysis Using Gray Level Lengths. Computer Graphics and Image Processing, 1975, 1(4): 172179 [4] Chu A, Sehgal C M, Greenleaf J F. Use of Gray Value Distribution of Run Lengths for Texture Analysis. Pattern Recognition Letters, 1990, 11(6): 415420 [5] Dasarathy B R, Holder E B. Image Characterizations Based on Joint GrayLevel RunLength Distributions. Pattern Recognition Letters, 1991, 12(8): 497502 [6] Pawlak Z. Rough Sets. International Journal of Information and Computer Science, 1982, 11(5): 145172 [7] Sun Lixin, Gao Wen. Method of Selecting the Best Classification Bands from Hyperspectral Images Based on Genetic Algorithm and Rough Set. Proc of SPIE, 1998, 3502: 179184 [8] Atkinson P M, Tatnall A R L. Neural Network in Remote Sensing. Remote Sensing, 1997, 18(4): 699709 [9] Yu Chunyan, Wu Minghui, Wu Ming. Combining Rough Set Theory with Neural Network for Remote Sensing Image. Journal of Remote Sensing, 2004, 8(4): 331338 (in Chinese) (余春艳,吴明辉,吴 明.遥感图像识别中粗糙集理论与神经网络的结合.遥感学报, 2004, 8(4): 331338) [10] Wu Zhaocong. RBFNN Representation Based on Rough Sets and Its Application to Remote Sensing Classification. Acta Geodaetica et Cartographica Sinica, 2003, 32(1): 5357 (in Chinese) (巫兆聪.基于粗糙理论的RBF网络及其遥感影像分类应用.测绘学报, 2003, 32(1): 5357)
2008, Vol. 21 
