SAR Image Target Recognition Based on Across Convolution Network Feature Fusion

Authors

Xinyang Feng, School of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450046, China;
Shao Chao, School of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450046, China;

Abstract

Abstract: Convolutional neural networks have been widely used in the field of synthetic aperture radar image target recognition. Based on the LeNet-5 neural network model, a SAR image target recognition method are initialized across convolution network feature fusion is proposed. The LeNet-5 network parameters on the basis of MNIST handwritten data. The deep and shallow features of the SAR image are extracted, and the principal component analysis on the shallow features is performed to obtain key category information. Deep features and shallow features are fused and are classified and recognised by sent to collaborative representation. Experimental results show that the method can achieve 98% average recognition rate without expanding the training samples.

Recommended Citation

Feng, Xinyang and Chao, Shao (2021) "SAR Image Target Recognition Based on Across Convolution Network Feature Fusion," Journal of System Simulation: Vol. 33: Iss. 3, Article 5.
DOI: 10.16182/j.issn1004731x.joss.19-0609
Available at: https://dc-china-simulation.researchcommons.org/journal/vol33/iss3/5

First Page

554

Revised Date

2020-05-18

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.19-0609

Last Page

561

CLC

TP183;TP391

Recommended Citation

Feng Xinyang, Shao Chao. SAR Image Target Recognition Based on Across Convolution Network Feature Fusion[J]. Journal of System Simulation, 2021, 33(3): 554-561.

DOI

10.16182/j.issn1004731x.joss.19-0609