Ocean surface feature extraction and targets detection from SAR images using neural network

In this paper, a novel system is presented for the targets detection from synthetic aperture radar (SAR) images of ocean. The proposed system consists of two neural networks. The first network cluster the extracted target fractal feature vectors in smaller sub-portions of the image, and the second GA RBF network integrates the information from the first network to determine the presence or absence of a target in the entire image.