A method of hyperspectral image classification based on posterior probability SVM and MRF

Author

Hong-Min Gao ; Meng-Xi Xu ; Ming-Gang Xu ; Xin Wang ; Feng-Chen Huang

Author_Institution

Coll. of Comput. & Inf. Eng., Hohai Univ., Nanjing, China

Volume

01

fYear

2013

fDate

14-17 July 2013

Firstpage

235

Lastpage

240

Abstract

In order to improve the accuracy of remote sensing image classification, this paper firstly improves the kernel function of support vector machines (SVMs), after which the Markov Random Field (MRF) stochastic model is combined with the SVM model to classify the images. The remote sensing experimental area in northwest Indiana is shot in June 1992. A VIRIS hyperspectral remote sensing images are used as an example to validate the classification algorithm, and the comparison and analysis are carried out with the traditional SVM and MRF. Experiments show that the new classification method can achieve higher classification accuracy.

Keywords

Markov processes; image classification; probability; support vector machines; MRF stochastic model; Markov random field; VIRIS hyperspectral remote sensing image classification algorithm; kernel function; posterior probability SVM; support vector machines; Abstracts; Distance measurement; Heating; Kernel; Polynomials; Remote sensing; Support vector machines; Image classification; MRF; SVM; kernel function;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2013 International Conference on

Conference_Location

Tianjin

Type

conf

DOI

10.1109/ICMLC.2013.6890474

Filename

6890474