Record Details


Field	Value

Title	Unsupervised classification of remote sensing data using graph cut-based initialization

Names	TYAGI, M MEHRA, AK CHAUDHURI, S BRUZZONE, L
Date Issued	2005 (iso8601)
Abstract	In this paper we propose a multistage unsupervised classifier which uses graph-cut to produce initial segments which are made up of pixels with similar spectral properties, subsequently labelled by a fuzzy c-means clustering algorithm into a known number of classes. These initial segmentation results are used as a seed to the expectation maximization (EM) algorithm. Final classification map is produced by using the maximum likelihood (ML) classifier, performance of which is quite good as compared to other unsupervised classification techniques.
Genre	Article; Proceedings Paper
Identifier	PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PROCEEDINGS,3776,206-211

ICAR Research Data Repository for Knowledge Management