SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images

• Published in: IEEE geoscience and remote sensing letters Vol. 7; no. 4; pp. 736 - 740
• Main Authors: Tarabalka, Y, Fauvel, M, Chanussot, J, Benediktsson, J A
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2010; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); IEEE - Institute of Electrical and Electronics Engineers
• Subjects: Classification; Computer Science; hyperspectral images; Hyperspectral imaging; Hyperspectral sensors; Image analysis; Image classification; Image Processing; Layout; Markov random field (MRF); Markov random fields; Pixel; Senior members; support vector machine (SVM); Support vector machine classification; Support vector machines; Markov random field (MRF); hyperspectral images; support vector machine (SVM); Classification
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2010.2047711

The high number of spectral bands acquired by hyperspectral sensors increases the capability to distinguish physical materials and objects, presenting new challenges to image analysis and classification. This letter presents a novel method for accurate spectral-spatial classification of hyperspectral images. The proposed technique consists of two steps. In the first step, a probabilistic support vector machine pixelwise classification of the hyperspectral image is applied. In the second step, spatial contextual information is used for refining the classification results obtained in the first step. This is achieved by means of a Markov random field regularization. Experimental results are presented for three hyperspectral airborne images and compared with those obtained by recently proposed advanced spectral-spatial classification techniques. The proposed method improves classification accuracies when compared to other classification approaches.