Feature selection for urban land cover classification employing genetic algorithm

Feature selection has attained substantial research interest in image processing, computer vision, pattern recognition and so on due to tremendous dimensional reduction analysis. This addresses a genetic algorithm based feature strategy for urban land cover classification. The principal purpose of this is monitor the alterations satellite imagery planning. method object classification by detecting area given with knowledge visual information from remote sensing images. system organized through multilayer perceptron (MLPGA). Experimental results explicitly indicate that MLPGA hybrid procedure performs sensitivity 94%, specificity 90% precision 89%, respectively. centered scheme attains better performance than counterpart methods terms accuracy.