Recognition of Sar Target Based on Multilayer Auto-encoder and Snn

Automatic target recognition (ATR) of synthetic aperture radar (SAR) image is investigated. One feature extraction algorithm of SAR image based on multilayer auto-encoder is proposed. The method makes use of a probabilistic neural network, restricted Boltzmann machine (RBM), modeling probability distribution of environment. Through the formation of more expressive multilayer neural network, the deep learning model learns shared representation of the target and its shadow to reflect the target shape. Targets are classified automatically through two classification models. The experiment results based on the MSTAR verify effectiveness of the proposed algorithm.