基于深度学习的银行卡号识别研究
Research on Identification of Bank Card Number Based on Deep Learning
摘要: 针对自然环境下银行卡卡号识别困难等问题,本文提出了一种基于深度学习的银行卡卡号识别方法。方法分为两步:银行卡卡号区域定位和定位后的卡号识别。卡号区域定位使用CTPN神经网络训练的数据模型,训练集数据采用ICDAR2015;对定位的银行卡号,使用CRNN神经网络训练数据模型,最后完成卡号数字识别。本方法采用端到端对银行卡卡号行定位、识别,能够自动适应图片的倾斜,对自然环境下银行卡卡号的识别具有很好的适应性。
Abstract:
In view of the difficulty in the identification of bank card numbers in natural environment, this paper proposes a method for the identification of bank card Numbers based on deep learning. The method is divided into two steps: the location of the bank card number and the identification of the card number after location. The data model of CTPN neural network was used for the location of card number area, and ICDAR2015 was used for the data of training set. The CRNN neural network was used to train the data model to locate the bank card number, and finally the card number digital recognition was completed. This method adopts end-to-end positioning and recognition of the bank card number line, which can automatically adapt to the tilt of the picture, and has good adaptability to the identification of bank card number in natural environment.
参考文献
|
[1]
|
涂亚飞. 银行卡号字符的分割与识别算法研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2017.
|
|
[2]
|
李淑云. 银行卡卡号字符分割与识别方法研究[D]: [硕士学位论文]. 武汉: 华中科技大学, 2014.
|
|
[3]
|
董延华, 陈中华, 宋和烨, 黄雨. 改进特征匹配算法在银行卡号识别中的应用[J]. 吉林大学学报(理学版), 2018, 56(1): 126-129.
|
|
[4]
|
赵慧敏. 基于深度学习的银行卡识别系统设计开发[D]: [硕士学位论文]. 北京: 华北电力大学, 2019.
|
|
[5]
|
刘振飞. 基于OpenCV的银行卡号识别系统[J]. 电子技术与软件工程, 2019(11): 63-63.
|
|
[6]
|
蔡安平, 邱博宇, 谭小辉, 李尚林. 基于移动端的银行卡识别方法[J]. 计算机科学与应用, 2020, 10(4): 732-740.
|
|
[7]
|
Tian, Z., Huang, W., He, T., et al. (2016) Detecting Text in Natural Image with Connectionist Text Proposal Network. ECCV 2016, 56-72. arXiv:1609.03605 [cs.CV] [Google Scholar] [CrossRef]
|
|
[8]
|
Liao, M., Lyu, P., He, M., et al. (2019) Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP(99), 1-1. [Google Scholar] [CrossRef]
|
|
[9]
|
Shi, B., Bai, X. and Yao, C. (2016) An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition. IEEE Trans-actions on Pattern Analysis & Machine Intelligence, 39, 2298-2304. [Google Scholar] [CrossRef]
|