A vector machine based approach towards object oriented classification of remotely sensed imagery
Remote sensing techniques are widely used for land cover classification and related analyses; however the availability of high resolution images have limited the accuracy of pixel based approaches. In this paper, we have analyzed the feasibility of incorporating contextual information to a support machine and have evaluated its performances with reference to the traditional approaches. We have adopted certain automatic approaches based on advanced techniques such as Cellular Automata and Genetic Algorithm for improving effective overlap between classes. Proposed methodology has been evaluated in comparison with the conventional approaches with reference to the study area using relevant statistical parameters. Accuracy improvement of the proposed approach may be attributed to the effectiveness in combining spatial and spectral information.