SAR target recognition based on Gabor filter and convolutional neural network

Chenlong Guo; YuXuan Han; HuiYing Zhang

doi:10.1117/12.2548117

27 November 2019 SAR target recognition based on Gabor filter and convolutional neural network

Chenlong Guo, YuXuan Han, HuiYing Zhang

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 1132118 (2019) https://doi.org/10.1117/12.2548117
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

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.

Citation Download Citation

Chenlong Guo, YuXuan Han, and HuiYing Zhang "SAR target recognition based on Gabor filter and convolutional neural network", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 1132118 (27 November 2019); https://doi.org/10.1117/12.2548117

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available