Supervised classification for object identification in urban areas using satellite imagery

Abstract

This paper presents a useful method to achieve classification in satellite imagery. The approach is based on pixel level study employing various features such as correlation, homogeneity, energy and contrast. In this study gray-scale images are used for training the classification model. For supervised classification, two classification techniques are employed namely the Support Vector Machine (SVM) and the Naïve Bayes. With textural features used for gray-scale images, Naïve Bayes performs better with an overall accuracy of 76% compared to 68% achieved by SVM. The computational time is evaluated while performing the experiment with two different window sizes i.e., 50 × 50 and 70 × 70. The required computational time on a single image is found to be 27 seconds for a window size of 70 × 70 and 45 seconds for a window size of 50 × 50.