End-to-End Bank Card Number Recognition Algorithm Based on DenseNet

被引:0
作者
Liu Yun [1 ]
Ma Ruidi [1 ]
Li Hui [1 ]
Cui Xuehong [1 ]
机构
[1] Qingdao Univ Sci & Technol, Qingdao, Shandong, Peoples R China
来源
2019 IEEE INTERNATIONAL WORKSHOP ON ELECTROMAGNETICS: APPLICATIONS AND STUDENT INNOVATION COMPETITION (IWEM2019) | 2019年
基金
美国国家科学基金会;
关键词
Card number recognition; DensenNet; End-to-End;
D O I
暂无
中图分类号
O59 [应用物理学];
学科分类号
摘要
Printed bank cards number, which are usually black and not easily confused with the background, is easy to split and recognize; embossed bank card, the color of bumped card number is similar to background, characters difficult to split and identify. This paper proposes an end-to-end bank card number recognition algorithm, first uses CTPN network for text detection, then sends the test results into the DenseNet network to identify, finally the card number is output according to the text length. Experimental results show that the algorithm can achieve the automatic identification of the two types of bank card, with high recognition rate and accuracy.
引用
收藏
页数:2
相关论文
共 5 条
[1]  
Cui Weiqing, 2018, MECH MANAGEMENT DEV, V11, P252
[2]   改进特征匹配算法在银行卡号识别中的应用 [J].
董延华 ;
陈中华 ;
宋和烨 ;
黄雨 .
吉林大学学报(理学版), 2018, 56 (01) :126-129
[3]   Densely Connected Convolutional Networks [J].
Huang, Gao ;
Liu, Zhuang ;
van der Maaten, Laurens ;
Weinberger, Kilian Q. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269
[4]  
Liu Zhenfei, 2019, ELECT TECHNOLOGY SOF, V11, P63
[5]   Detecting Text in Natural Image with Connectionist Text Proposal Network [J].
Tian, Zhi ;
Huang, Weilin ;
He, Tong ;
He, Pan ;
Qiao, Yu .
COMPUTER VISION - ECCV 2016, PT VIII, 2016, 9912 :56-72