Image Classification using SOM and SVM Feature Extraction

Support Vector Machines (SVMs) are a relatively new supervised classification technique to the land cover mapping community.SVM are machine learning techniques that are used for segmentation and classification of medical pictures, as well as segmentation of white matter hyperintensities (WMH). Although there are various techniques implemented for the classification of image, here combinatorial method of clustering and classification. Here the feature extraction using SVM based training is performed while SOM clustering is used for the clustering of these feature values. The proposed methodology for the image classification provides high accuracy as compared to the existing technique for image classification.