Share Email Print
cover

Journal of Electronic Imaging

Albedo recovery for hyperspectral image classification
Author(s): Kun Zhan; Haibo Wang; Yuange Xie; Chutong Zhang; Yufang Min
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Image intensity value is determined by both the albedo component and the shading component. The albedo component describes the physical nature of different objects at the surface of the earth, and land-cover classes are different from each other because of their intrinsic physical materials. We, therefore, recover the intrinsic albedo feature of the hyperspectral image to exploit the spatial semantic information. Then, we use the support vector machine (SVM) to classify the recovered intrinsic albedo hyperspectral image. The SVM tries to maximize the minimum margin to achieve good generalization performance. Experimental results show that the SVM with the intrinsic albedo feature method achieves a better classification performance than the state-of-the-art methods in terms of visual quality and three quantitative metrics.

Paper Details

Date Published: 26 July 2017
PDF: 12 pages
J. Electron. Imag. 26(4) 043010 doi: 10.1117/1.JEI.26.4.043010
Published in: Journal of Electronic Imaging Volume 26, Issue 4
Show Author Affiliations
Kun Zhan, Lanzhou Univ. (China)
Haibo Wang, Lanzhou Univ. (China)
Yuange Xie, Lanzhou Univ. (China)
Chutong Zhang, Huazhong Univ. of Science and Technology (China)
Yufang Min, Chinese Academy of Sciences (China)


© SPIE. Terms of Use
Back to Top