
Proceedings Paper
Spatial-spectral metric learning for hyperspectral remote sensing image classificationFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
A spatial-spectral metric learning (SSML) framework for hyperspectral image (HSI) classification is proposed. SSML learns a metric by considering both the spectral characteristics and spatial features represented as the mean of neighboring pixels. It first performs the local pixel neighborhood preserving embedding (LPNPE) to reduce the dimensionality of HSI and meanwhile to preserve the spatial local similarity structure. Then, it learns a spectral and spatial distance metric, separately. Finally, the combination of the spectral and spatial metrics yields a joint spatial-spectral metric. It is followed by a nearest neighbor (NN) classifier for HSI classification. SSML shows good performance over the spectral and spatial NN and SVM on the benchmark hyperspectral data set of Indian Pines.
Paper Details
Date Published: 15 September 2014
PDF: 7 pages
Proc. SPIE 9222, Imaging Spectrometry XIX, 92220K (15 September 2014); doi: 10.1117/12.2060309
Published in SPIE Proceedings Vol. 9222:
Imaging Spectrometry XIX
Pantazis Mouroulis; Thomas S. Pagano, Editor(s)
PDF: 7 pages
Proc. SPIE 9222, Imaging Spectrometry XIX, 92220K (15 September 2014); doi: 10.1117/12.2060309
Show Author Affiliations
Jiangtao Peng, Hubei Univ. (China)
Univ. of Macau (Macao, China)
Yicong Zhou, Univ. of Macau (Macao, China)
Univ. of Macau (Macao, China)
Yicong Zhou, Univ. of Macau (Macao, China)
C. L. Philip Chen, Univ. of Macau (Macao, China)
Published in SPIE Proceedings Vol. 9222:
Imaging Spectrometry XIX
Pantazis Mouroulis; Thomas S. Pagano, Editor(s)
© SPIE. Terms of Use
