[1]卢用煌,黄山.深度学习在身份证号码识别中的应用[J].应用科技,2019,46(01):123-128.[doi:10.11991/yykj.201804008]
 LU Yonghuang,HUANG Shan.Application of deep learning in identification of ID card number[J].Applied science and technology,2019,46(01):123-128.[doi:10.11991/yykj.201804008]
点击复制

深度学习在身份证号码识别中的应用(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第46卷
期数:
2019年01期
页码:
123-128
栏目:
计算机技术与应用
出版日期:
2019-01-05

文章信息/Info

Title:
Application of deep learning in identification of ID card number
作者:
卢用煌1 黄山2
1. 四川大学 电气信息学院, 四川 成都 610065;
2. 四川大学 计算机学院, 四川 成都 610065
Author(s):
LU Yonghuang1 HUANG Shan2
1. College of Electrical Engineering and Information, Sichuan University, Chengdu 610065, China;
2. College of Computer Science, Sichuan University, Chengdu 610065, China
关键词:
光学字符识别深度学习身份证识别卷积神经网络神经网络字符识别k最近邻分类算法模型优化
Keywords:
optical character recognitiondeep learningidentity card number recognitionCNNneural networkcharacter recognitionk-NearestNeighbormodel optimization
分类号:
TP391
DOI:
10.11991/yykj.201804008
文献标志码:
A
摘要:
为了克服传统身份证文字识别算法提取特征难的问题,提出一种基于深度学习的身份证号码识别方法。先通过OSTU实现文字区域的提取,再通过投影统计法切割单个文字的图片,分别从神经元数量、网络层深浅的变化分析网络模型的识别效果。从动态学习率、抑制过拟合和损失函数设计等方面对网络模型进行优化,提升了模型识别正确率。实验结果表明,结合优化策略的卷积神经网络的识别正确率能达到99.96%。
Abstract:
In order to overcome the difficulty of extracting characteristics by traditional ID card character recognition algorithm, an ID card number recognition method based on deep learning was proposed. First, the text area was extracted through OSTU, and then the single text was cut through projection statistics. The recognition effect of network model was analyzed from the number of neurons and the depth of network layer. The network model was optimized from aspects of dynamic learning rate, suppression of over fitting and loss function design, etc., which improves the accuracy of model recognition. Experimental results show that the recognition accuracy of convolution neural network combined with optimization strategy can reach 99.96%.

参考文献/References:

[1] 刘建伟, 刘媛, 罗雄麟. 深度学习研究进展[J]. 计算机应用研究, 2014, 31(7):1921-1930, 1942.
[2] 郭丽丽, 丁世飞. 深度学习研究进展[J]. 计算机科学, 2015, 42(5):28-33.
[3] CYBENKO G. Approximation by superpositions of a sigmoidal function[J]. Approximation theory and its applications, 1993, 9(3):17-28.
[4] 金连文, 钟卓耀, 杨钊, 等. 深度学习在手写汉字识别中的应用综述[J]. 自动化学报, 2016, 42(8):1125-1141.
[5] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015:1026-1034.
[6] 卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理, 2016, 31(1):1-17.
[7] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, 2012:1097-1105.
[8] LÉCUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[9] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille, France, 2015:448-456.
[10] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. arXiv:1207.0580, 2012.
[11] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[12] 胡正平, 陈俊岭, 王蒙, 等. 卷积神经网络分类模型在模式识别中的新进展[J]. 燕山大学学报, 2015, 39(4):283-291.
[13] 赵志宏, 杨绍普, 马增强. 基于卷积神经网络LeNet-5的车牌字符识别研究[J]. 系统仿真学报, 2010, 22(3):638-641.
[14] 李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9):2508-2515, 2565.

相似文献/References:

[1]王信,汪友生.基于深度学习与传统机器学习的人脸表情识别综述[J].应用科技,2018,45(01):65.[doi:10.11991/yykj.201707008]
 WANG Xin,WANG Yousheng.Facial expression recognition based on deep learning and traditional machine learning[J].Applied science and technology,2018,45(01):65.[doi:10.11991/yykj.201707008]
[2]宋佳蓉,杨忠,张天翼,等.基于卷积神经网络和多类SVM的交通标志识别[J].应用科技,2018,45(05):71.[doi:10.11991/yykj.201710009]
 SONG Jiarong,YANG Zhong,ZHANG Tianyi,et al.Traffic signs recogniton based on convolutional neural networks and multi-class SVM[J].Applied science and technology,2018,45(01):71.[doi:10.11991/yykj.201710009]
[3]王立新,江加和.基于深度学习的显著性区域的图像检索研究[J].应用科技,2018,45(06):63.[doi:10.11991/yykj.201803012]
 WANG Lixin,JIANG Jiahe.Research on image retrieval of saliency region based on deep learning[J].Applied science and technology,2018,45(01):63.[doi:10.11991/yykj.201803012]
[4]陈聪,杨忠,宋佳蓉,等.一种改进的卷积神经网络行人识别方法[J].应用科技,2019,46(03):51.[doi:10.11991/yykj.201809014]
 CHEN Cong,YANG Zhong,SONG Jiarong,et al.An improved pedestrian detection method based on convolutional neural network[J].Applied science and technology,2019,46(01):51.[doi:10.11991/yykj.201809014]

备注/Memo

备注/Memo:
收稿日期:2018-4-15。
作者简介:卢用煌,男,硕士研究生;黄山,男,教授,博士生导师.
通讯作者:卢用煌,E-mail:luyonghuang@outlook.com
更新日期/Last Update: 2019-03-05