Content driven dimensionality reduction at block level in the design of an efficient classifier for spatial multi spectral images

Rangarajan, L. and Nagabhushan, P. (2004) Content driven dimensionality reduction at block level in the design of an efficient classifier for spatial multi spectral images. Pattern Recognition Letters, 25 (16). pp. 1833-1844. ISSN 0167-8655

Text (Full Text) Cmp_2004_Lalitha_Nagabhushan_02pdf.pdf - Published Version Restricted to Registered users only Download (450kB) | Request a copy

Abstract

In case of spatial multi spectral images, such as remotely sensed earth cover, there could be many classes in one entire frame covering a large spatial stretch, because of which meaningful dimensionality reduction cannot perhaps be realizable without trading off with the quality of classification. However most often one would encounter in such images, presence of only a few classes in a small neighborhood, which would enable to devise a very effective dimensionality reduction around that small neighborhood identified as a block. Based on this theme a new method for dimensionality reduction is proposed in this paper. The method proposed divides the image into uniform non-overlapping windows/blocks. The few features that are essential in discriminating classes in a window are identified. Clustering is performed independently on each of the blocks with the reduced set of features. These clusters in the blocks are later merged to obtain an overall classification of the entire image. The efficacy of the method is corroborated experimentally. (C) 2004 Elsevier B.V. All rights reserved.

Item Type:	Article
Uncontrolled Keywords:	multi spectral images; remote sensing; dimensionality reduction; pattern classification; local clustering; global clustering
Subjects:	D Physical Science > Computer Science
Divisions:	Department of > Computer Science
Depositing User:	Users 23 not found.
Date Deposited:	05 Sep 2019 06:13
Last Modified:	05 Sep 2019 06:13
URI:	http://eprints.uni-mysore.ac.in/id/eprint/6519

Actions (login required)

View Item