Optimization of Convolutional Neural Network Target Recognition Algorithm

	Optimization of Convolutional Neural Network Target Recognition Algorithm
	Guo, Chen; Jiang, Yuanyuan
	2018
会议日期	SEP 18-20, 2018
会议地点	Kunming, PEOPLES R CHINA
关键词	Convolutional neural networks Deep learning principal component analysis
卷号	306
页码	426-433
英文摘要	This paper proposes an optimized convolutional neural network target recognition algorithm for the problem of low recognition rate of synthetic aperture radar (SAR) target training, under the condition of insufficient tag data, translation, rotation and complexity. In order to overcome the shortage of tag data, the convolutional neural network is initialized with a feature set, obtained by principal component analysis (PCA) unsupervised training. In order to improve the training speed while avoiding overfitting, Rectified Linear Unit (ReLU) function is used as the activation function. In order to enhance robustness and reduce the effect of down sampling on feature representation, this work uses a maximum probability sampling method and normalizes the local contrast of feature after convolution layers. The experimental result shows that, compared with traditional convolutional neural network, this approach achieves a higher recognition rate for SAR target and better robustness to various image deformation and complex background.
会议录	14TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, NETWORKING AND MOBILE COMPUTING (WICOM 2018)
语种	英语
ISSN号	2475-8841
ISBN号	978-1-6059-5578-0
内容类型	会议论文
源URL	[http://ir.nssc.ac.cn/handle/122/6680]
专题	国家空间科学中心_空间技术部
推荐引用方式 GB/T 7714	Guo, Chen,Jiang, Yuanyuan. Optimization of Convolutional Neural Network Target Recognition Algorithm[C]. 见:. Kunming, PEOPLES R CHINA. SEP 18-20, 2018.