Title: Spectral and spatial feature classification of hyperspectral images based on particle swarm optimisation
Authors: Sheng Ding; Li Chen
Addresses: College of Computer Science and Technology, Wuhan University of Science and Technology, No. 947 Heping Road, Qingshan District, Wuhan, China. ' College of Computer Science and Technology, Wuhan University of Science and Technology, No. 947 Heping Road, Qingshan District, Wuhan, China
Abstract: This paper addresses the problem of feature selection and SVM kernel parameter optimisation for hyperspectral remote sensing image. First, we propose an evolutionary classification algorithm based on particle swarm optimisation (PSO) to improve the generalisation performance of the SVM classifier. For this purpose, we have optimised the SVM classifier design by searching for the best value of the kernel parameters of SVM that tune its discriminant function, and upstream by looking for the best subset of features that feed the classifier. Second, we propose a feature fusion approach based on the joint use of spectral and spatial information provided by texture features extracted from the grey level co-occurrence matrix (GLCM). Experimental results prove that spectral feature and GLCM texture features can obtain higher classification accuracy than only spectral feature classification for hyperspectral image classification.
Keywords: support vector machine; SVM; particle swarm optimisation; PSO; feature selection; grey level co-occurrence matrix; GLCM; spatial feature classification; spectral feature classification; hyperspectral images; remote sensing; texture features; image classification.
International Journal of Innovative Computing and Applications, 2012 Vol.4 No.3/4, pp.233 - 242
Available online: 25 Oct 2012 *Full-text access for editors Access for subscribers Purchase this article Comment on this article