Deep Learning for Optical Character Recognition and Its Application to VAT Invoice Recognition

被引：2

作者：

Wang, Yu ^{[1
]}

Gui, Guan ^{[1
]}

Zhao, Nan ^{[1
]}

Yin, Yue ^{[1
]}

Huang, Hao ^{[1
]}

Li, Yunyi ^{[1
]}

Wang, Jie ^{[1
]}

Yang, Jie ^{[1
]}

Zhang, Haijun ^{[1
]}

机构：

[1] Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing 21003, Peoples R China

来源：

COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, CSPS 2018, VOL III: SYSTEMS | 2020年 / 517卷

关键词：

Optical character recognition; Value-added tax invoices; Deep learning; Convolutional neural network; Residuals network; TEXT;

D O I：

10.1007/978-981-13-6508-9_12

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Optical character recognition (OCR) is considered as one of long-term and hot research topics due to the fact that OCR technique can change the documents from paper to computer-readable format by consistently growing. However, the recognition accuracy of current OCR technique is required to improve some special applications such as in reimbursement of value-added tax (VAT) invoices. This paper proposes two OCR techniques by using deep convolutional neural network (CNN) and residual network (ResNet), respectively. According to our test dataset, the formerly proposed techniques can reach up to 97.08%, while the latter can increase to 99.38%.

引用

页码：87 / 95

页数：9

共 12 条

[1] OCR binarization and image pre-processing for searching historical documents [J].

Gupta, Maya R. ;

Jacobson, Nathaniel P. ;

Garcia, Eric K. .

PATTERN RECOGNITION, 2007, 40 (02) :389-397

[2] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[3]

Krizsan A, 2012, GENDER POLIT, P1

[4]

Modi H, 2017, INT J COMPUT APPL, V160, P975

[5]

Mohammad F., 2014, Em: International Journal of Computer Science and Information Technologies, V5, P2088

[6]

Ohta M, 1997, PROC INT CONF DOC, P950, DOI 10.1109/ICDAR.1997.620651

[7]

Sawant AS, 2015, 2015 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS, SIGNALS, COMMUNICATION AND OPTIMIZATION (EESCO)

[8] An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition [J].

Shi, Baoguang ;

Bai, Xiang ;

Yao, Cong .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (11) :2298-2304

[9] EDGE LOCATION TO SUBPIXEL VALUES IN DIGITAL IMAGERY [J].

TABATABAI, AJ ;

MITCHELL, OR .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (02) :188-201

[10]

Vairalkar M.K., 2012, Int. J. Emerg. Technol. Adv. Eng, V2, P291

← 1 2 →