Global Advanced Research Journal of Agricultural Science (GARJAS) ISSN: 2315-5094
November 2015 Vol. 4(11): pp. 810-818
Copyright © 2015 Global Advanced Research Journals


Full Length Research Paper

A Comparison of Classification Techniques for the Land Use/ Land Cover Classification 

R. S. Morgan*a, I. S. Rahim*a, M. Abd El-Hady*b


*aSoils and Water Use dept., *b Water Relations and Field irrigation Dept.,

National Research Centre, El Behouth St., Dokki, Cairo


Accepted 29 November, 2015



Land use/land cover classification plays an important role in the sustainable management of the natural resources. Remote sensing techniques have been intensively used for land use /land cover classification. Over the last decade new technologies had emerged that increased the accuracy of the produced maps. The aim of this work is to investigate for an effective image classifier by comparing three classifiers i.e. Maximum Likelihood classifier (MLC), Artificial Neural Network (ANN) and Support Vector Machine (SVM) for land use/ land cover classification for a selected area in the north of the Delta of  Egypt. In  this work, the surface reflectance data of  Landsat 7  ETM+  was used. To  reduce the redundancy in the data, the Principal Component Analysis (PCA) was used and the first three PCAs were selected for further analysis. The accuracy of the three classification method was compared using the confusion matrix. In this work the overall accuracy of ANN was not satisfactory using both the ENVI's Neural Net and the neural network Pattern Recognition tool of Matlab and therefore was not recommended in  this study area. The overall accuracy for MLC and SVM was 80.28 and80.64 %, respectively. Both MLC and SVM showed similar overall accuracy with an advantage of MLC when considering the producer and user accuracy. To enhance the classification results, the Normalized Difference Water Index (NDWI) was included and the MLC and SVM were re-examined. This addition enhanced the overall accuracy of MLC to 83.95 % while the SVM decreased to 79.03%. Thus, it is recommended using the MLC when classifying the land use/ land cover in this study area using the same approach.

KeywordsMaximum likelihood classification, artificial neural networks, support vector machine, land use/ land cover, image classification



Related Articles

Original Research Articles
R. S. Morgan, I. S. Rahim, M. Abd El-Hady
Utilization of Change Vector Analysis for Land Use/ Land Cover Change Detection in a Selected Area in the Northern Delta, Egypt
Glo. Adv. Res. J. Agric. Sci. November 2015 Vol: 4(11): - [Abstract] [Full Text - PDF] (4,039 KB)
Kedir Jemal
Effects of Different Land Use System on Physico-Chemical Properties of Soil in Wudma Sub watershed District, Southern Ethiopia
Glo. Adv. Res. J. Agric. Sci. June 2020 Vol: 9(6): - [Abstract] [Full Text - PDF] (177 KB)

Current Issue

Viewing Options

View Full Article - PDF
Download Full Article - PDF

Search for Articles

R. S. Morgan on Google Scholar
R. S. Morgan on Pubmed
I. S. Rahim on Google Scholar
I. S. Rahim on Pubmed
M. Abd El-Hady on Google Scholar
M. Abd El-Hady on Pubmed


Viewed 2578
Printed 1170
Downloaded 4120
Powered By iPortal Works