Classification of Local SAR Features with Convolutional Neural Network

Abstract

Convolutional neural network extracts features from input data and classify them with end to end learning. In this paper we test the performance of the cooperation between texture features which undertakes effective role for SAR image classification and convolutional neural network. For this purpose we create local images for each pixel in the image taking into consideration neighbor pixels and pixel-based classification is performed with convolutional neural network after being extracted histogram and texture feautures from these images. Experimental results show that the network trained with feature vectors gives high classification accuracy.