Hyperspectral Remote Sensing Images Classification Method Based on Learned Dictionary

DOI

10.2991/isca-13.2013.60How to use a DOI?

Keywords

hyperspectral, image classification, sparse representation, learned dictionary

Abstract

A novel hyperspectral image classification method based on learned dictionary is presented in this paper. Firstly, the sampled image pixel and its classification vector are combined as sample pair. Secondly, defined as a sample vector, the sample pair are used for sparse coding and dictionaries learning. Then, the sparse association between sample pairs is established efficiently. Finally, defined as prior knowledge, the sparse association is used to guide the classification of input image. The whole dictionary learning process can be achieved offline, and improve the speed of the algorithm. Several experiments show that the method can get good classification results.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Min Li
AU  - Jun Shen
AU  - Lianjun Jiang
PY  - 2013/10
DA  - 2013/10
TI  - Hyperspectral Remote Sensing Images Classification Method Based on Learned Dictionary
BT  - Proceedings of 2013 International Conference on Information Science and Computer Applications
PB  - Atlantis Press
SP  - 357
EP  - 362
SN  - 1951-6851
UR  - https://doi.org/10.2991/isca-13.2013.60
DO  - 10.2991/isca-13.2013.60
ID  - Li2013/10
ER  -