Click here to view fulltext PDF

Permanent link:
https://www.ias.ac.in/article/fulltext/jess/122/05/1237-1247

Remote sensing; image classification; decision tree classifier (DTC); maximum likelihood classifier (MLC); ISODATA.

In this study, an attempt has been made to develop a decision tree classification (DTC) algorithm for classification of remotely sensed satellite data (Landsat TM) using open source support. The decision tree is constructed by recursively partitioning the spectral distribution of the training dataset using WEKA, open source data mining software. The classified image is compared with the image classified using classical ISODATA clustering and Maximum Likelihood Classifier (MLC) algorithms. Classification result based on DTC method provided better visual depiction than results produced by ISODATA clustering or by MLC algorithms. The overall accuracy was found to be 90% (kappa = 0.88) using the DTC, 76.67% (kappa = 0.72) using the Maximum Likelihood and 57.5% (kappa = 0.49) using ISODATA clustering method. Based on the overall accuracy and kappa statistics, DTC was found to be more preferred classification approach than others.

Richa Sharma¹ Aniruddha Ghosh¹ P K Joshi¹

1. Department of Natural Resources, TERI University, New Delhi 110 070, India.

Published

October 2013

Manuscript received

21 November 2012

Manuscript revised

15 February 2013

Accepted

25 February 2013