A Design Entropy Based Hybrid Soft Classifier Algorithms for Improving Classification Performance of a Satellite Data

Authors : Ranjana Sharma, P. K. Garg, R. K. Dwivedi

Pages : 117-124

Doi:10.33187/jmsm.459653

View : 20 | Download : 13

Publication Date : 2019-08-30

Article Type : Research

Abstract :Image classification of the satellite imagery interprets the thematic map to represent the spatial distribution of earth features. There are so many applications of Remote sensing image classification such as Resource utilization and environmental impact analysis etc. The overall process result depends on two main aspects Every object have distinctive signature and feature of interest The process can distinguish these features separately. Image classification is broadly classified in two ways Pure classification and Mixed classification. In the pure classification, the pixels are classified into class only and in the mixed classification, pixels can fit into one or more module according to their membership values. In hard classification, data may be lost because of the restriction being in a single class. However in the soft classification, this problem is resolved. After resolving the problem, there is a need of accuracy assessment. Accuracy parameter is very important factor in terms of classification. So, in this study, I am trying to design the algorithm for the hybridization classification with entropy to maintain the optimizing.
Keywords : Accuracy, Entropy, Fuzzy C-Means with entropy