Share Email Print
cover

Proceedings Paper • new

SAR target recognition based on Gabor filter and convolutional neural network
Author(s): Chenlong Guo; YuXuan Han; HuiYing Zhang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, a synthetic aperture radar target recognition method based on Gabor filter and convolutional neural network was proposed. Ordinary convolutional neural network obtained the corresponding connection weight through self-learning, but it had no clear meaning, and often required more convolution kernels and more time cost to complete the self-learning of features. Due to the local amplification function of Gabor filter, it was used as the fixed connection weight as the first convolution kernel of the convolutional neural network in this paper. Then, a convolutional neural network consisting of 7 convolutional layers and 2 full-connected layers was constructed, and the convolutional neural network was used for SAR target recognition. Experimental results showed that, after adding Gabor filter as the fixed first convolutional layer, the convergence rate of convolutional neural network could be greatly improved, and the recognition effect is better than that of ordinary convolutional neural network.

Paper Details

Date Published: 27 November 2019
PDF: 7 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 1132118 (27 November 2019); doi: 10.1117/12.2548117
Show Author Affiliations
Chenlong Guo, Luoyang Electro-optical Equipment Research Institute (China)
YuXuan Han, Chongqing Univ. (China)
HuiYing Zhang, Dalian Univ. of Technology (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top