International Journal of Engineering and Technology

In this study, the pixel-based and object-oriented image classification approaches were used for identifying different land use types in Karnal district. Imagery from Landsat-7 ETM with 6 spectral bands was used to perform the image classification. Ground truth data were collected from the available maps, personal knowledge and communication with the local people. In order to prepare land use map different approaches: Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used. For performing object oriented classification eCognition software was used. During the object oriented classification, in first step several different sets of parameters were used for image segmentation and in second step nearest neighbor classifier was used for classification. Outcome from the classification works show that the object-oriented approach gave more accurate results (including higher producer's and user's accuracy for most of the land cover classes) than those achieved by pixel-based classification algorithms. It is also observed that ANN performed better as compared to SVM classification approach.