Share Email Print

Proceedings Paper

Hyperspectral image classification using a spectral-spatial sparse coding model
Author(s): Ender Oguslu; Guoqing Zhou; Jiang Li
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We present a sparse coding based spectral-spatial classification model for hyperspectral image (HSI) datasets. The proposed method consists of an efficient sparse coding method in which the l1/lq regularized multi-class logistic regression technique was utilized to achieve a compact representation of hyperspectral image pixels for land cover classification. We applied the proposed algorithm to a HSI dataset collected at the Kennedy Space Center and compared our algorithm to a recently proposed method, Gaussian process maximum likelihood (GP-ML) classifier. Experimental results show that the proposed method can achieve significantly better performances than the GP-ML classifier when training data is limited with a compact pixel representation, leading to more efficient HSI classification systems.

Paper Details

Date Published: 17 October 2013
PDF: 6 pages
Proc. SPIE 8892, Image and Signal Processing for Remote Sensing XIX, 88920R (17 October 2013); doi: 10.1117/12.2030261
Show Author Affiliations
Ender Oguslu, Old Dominion Univ. (United States)
Guoqing Zhou, Guilin Univ. of Technology (China)
Jiang Li, Old Dominion Univ. (United States)

Published in SPIE Proceedings Vol. 8892:
Image and Signal Processing for Remote Sensing XIX
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top