A new algorithm of SAR target recognition based on advance deep learning neural network

Hui Xu, Hong Gu

COMPUTER MODELLING & NEW TECHNOLOGIES 2014 18(12A) 25-30

Nanjing University of Science & Technology, Jiangsu Nanjing China, 210094

In order to improve the accuracy of synthetic aperture radar images target recognition, we have proposed a new algorithm of SAR target recognition based on advance Deep Learning neural network. The traditional radar recognition algorithm has many disadvantages, In order to improve the accuracy of synthetic aperture radar images target recognition, the author have proposed a new algorithm of SAR target recognition based on advance Deep Learning neural network. In this paper, the author have got the feature of SAR image through the Refine Lee filter and HOG transformation firstly, and then realized the SAR object segmentation and recognition through the multi-layers RBM machine and GRNN neural network. and then realized the SAR object segmentation and recognition through the multi-layers RBM machine and GRNN neural network, and the learning rate parameter of the multi- layers RBM machine is optimized through the GA algorithm. The simulation results shows that the object recognition rate of the algorithm proposed in this paper can reach 97%, which can improve the performance of the algorithm obviously.