Authors: K. Radhika; S. Varadarajan; Y. Muralimohanbabu
Addresses: ECE Department, JNTUK, Kakinada, AP, 533003, India ' Andhra Pradesh State Council of Higher Education (APSCHE), AP, 517502, India ' ECE Department, SVCET, Chittoor, AP, 517127, India
Abstract: Satellite image classification is an imperative system utilised as a part of remote sensing. Primary data of extraordinary significance to different difficulties can be acquired straightforwardly from Land-cover observation. Different information partitions inferred by various clustering methods can be gathered into a new solution by cluster ensembles. Supervised iterative expectation-maximisation (EM) method can be initialised by cluster ensemble based strategy which will be examined in the paper. The performance of clustering of the proposed method is compared with individual clustering of the ensemble for medium resolution and a very high spatial resolution images. The accuracy measurements have done with different test points. The state of art techniques are giving less accuracy and are not well defined. This paper will explore the possibility of all accuracy parameters with supervised classification results. The accuracy parameters are well tested and compared in this paper with various start of art techniques.
Keywords: classification; image; satellite; ensemble; resolution; accuracy; kappa; multi spectral; classifier; validation.
International Journal of Intelligent Systems Technologies and Applications, 2018 Vol.17 No.1/2, pp.55 - 69
Received: 04 Feb 2017
Accepted: 09 Apr 2017
Published online: 03 May 2018 *