Small Sample Image Recognition Based on CNN and RBFNN

doi:10.3966/160792642020052103025

CORC > 深海科学与工程研究所 > 中国科学院深海科学与工程研究所 > 深海工程技术部 > 深海视频技术研究室

	Small Sample Image Recognition Based on CNN and RBFNN
	Yao, Biyuan 1; Zhou, Hui 2; Yin, Jianhua 3; Li, Guiqing 1; Lv, Chengcai 4
刊名	JOURNAL OF INTERNET TECHNOLOGY
	2020
卷号	21 期号:3 页码:881-889
关键词	Image recognition TensorFlow Fourier transform Roberts operator CNN RBFNN
ISSN号	1607-9264
DOI	10.3966/160792642020052103025
英文摘要	Identification of dangerous goods based on images plays a key role in the security inspection of various situations such as airports, subways, public places etc. This paper discusses the issue in a from-simple-to-complex manner. Firstly, we classify different kinds of knives given an image including a single object without complex background in the framework of TensorFlow. Then, according to the color and shape features of a single image, where Fourier transform and Roberts operator is used to judge of the complex scene which doesn't contain knives from an image with natural background. Finally, convolution neural network (CNN) and radial basis function neural network (RBFNN) are used to construct identification models for images of objects in six categories. The obtained accuracy of the true and predicted values of the CNN and RBFNN are 66.67% for training on CNN and 76.67% on RBFNN, for testing 50% on CNN and 44.44% on RBFNN respectively. The results showed that the constructed of identification model is able to perform recognition for small-scale image database and reduce the false alarm rate. Furthermore, our method is robust in dealing with the small sample, with high classification accuracy and low cost. The models have few layers and nodes.
资助项目	National Natural Science Foundation of China[61662019] ; Natural Science Foundation of Hainan Province[117212] ; Nature Science Foundation of Guangdong Province[2017A030313347]
WOS关键词	NEURAL-NETWORK
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	LIBRARY & INFORMATION CENTER, NAT DONG HWA UNIV
WOS记录号	WOS:000540310600027
资助机构	National Natural Science Foundation of China ; Natural Science Foundation of Hainan Province ; Nature Science Foundation of Guangdong Province
内容类型	期刊论文
源URL	[http://ir.idsse.ac.cn/handle/183446/7768]
专题	深海工程技术部_深海视频技术研究室
通讯作者	Zhou, Hui
作者单位	1.South China Univ Technol, Sch Comp Sci & Engn, Guangzhou, Guangdong, Peoples R China 2.Hainan Univ, Sch Comp Sci & Cyberspace Secur, Haikou, Hainan, Peoples R China 3.Hainan Univ, Sch Sci, Haikou, Hainan, Peoples R China 4.Chinese Acad Sci, Inst Deep Sea Sci & Engn, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Yao, Biyuan,Zhou, Hui,Yin, Jianhua,et al. Small Sample Image Recognition Based on CNN and RBFNN[J]. JOURNAL OF INTERNET TECHNOLOGY,2020,21(3):881-889.
APA	Yao, Biyuan,Zhou, Hui,Yin, Jianhua,Li, Guiqing,&Lv, Chengcai.(2020).Small Sample Image Recognition Based on CNN and RBFNN.JOURNAL OF INTERNET TECHNOLOGY,21(3),881-889.
MLA	Yao, Biyuan,et al."Small Sample Image Recognition Based on CNN and RBFNN".JOURNAL OF INTERNET TECHNOLOGY 21.3(2020):881-889.