SAR image target recognition based on GBMLWM algorithm and Bayesian neural networks

In this paper, a novel algorithm for target recognition in Synthetic Aperture Radar (SAR) images is proposed, which is the global between maximum and local within minimum (GBMLWM) feature extraction algorithm. Our proposed algorithm not only considers the global structure of the data set, but also makes the best of the local geometry of the data set through dividing the data set into four domains. Therefore, the effect of the new algorithm is better than the traditional algorithm in theory. Paper will put forward the new algorithm applied in the task of synthetic aperture radar image target recognition. Experimental results indicate that there are significant target recognition performance benefits in the probability of correct classification when GBMLWM algorithm is applied and Bayesian neural networks (BNN) is used.