ANN and SVM Based War Scene Classification Using Invariant Moments and GLCM Features: A Comparative Study
Daniel Madan Raja S, A. Shanmugam · International Journal of Machine Learning and Computing · 2012
Scene classification underlies many problems in visual perception such as object recognition and environment navigation.In this paper we are trying to classify a war scene from the natural scene.For this purpose two set of image categories are taken viz., opencountry & war tank.By using Invariant Moments and Gray Level Co-occurrence Matrix (GLCM), features are extracted from the images.The extracted features are trained and tested with (i) Artificial Neural Networks (ANN) using feed forward back propagation algorithm and (ii) Support Vector Machines (SVM) using radial basis kernel function with p=5.The comparative results are proving efficiency of Support Vector Machines towards war scene classification problems by using GLCM feature extraction method.Although this study has been the first step of the research in the area of scene classification, the results have shown that the war scenes can be successfully classified from opencountry.It can be concluded that the proposed work significantly and directly contributes to scene classification and its new applications.The complete work is experimented in Matlab 7.6.0using real world dataset.