MC-OCR Challenge 2021: An end-to-end recognition framework for Vietnamese Receipts

被引：1

作者：

Hung Le ^{[1
]}

Huy To ^{[1
]}

Hung An ^{[1
]}

Khanh Ho ^{[1
]}

Khoa Nguyen ^{[1
]}

Thua Nguyen ^{[1
]}

Tien Do ^{[1
]}

Thanh Duc Ngo ^{[1
]}

Duy-Dinh Le ^{[1
]}

机构：

[1] VNU HCMC, Univ Informat Technol, Fac Comp Sci, Ho Chi Minh City, Vietnam

来源：

2021 RIVF INTERNATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION TECHNOLOGIES (RIVF 2021) | 2021年

关键词：

Deep learning; OCR; Receipt;

D O I：

10.1109/RIVF51545.2021.9642121

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recognizing text from receipts is a significant step in automating office processes for many fields such as finance and accounting. MC-OCR Challenge has formed this problem into two tasks (1) evaluating the quality, and (2) recognizing required fields of the captured receipt. Our proposed framework is based on three key components: preprocessing with receipt detection using Faster R-CNN, alignment based on the angle and direction of rotation; estimate the receipt image quality score in task 1 using EfficientNet-B4 which has been retrained using transfer learning; while PAN is for text detection and VietOCR 1 for text recognition. In the final round, our systems have achieved the best result in task 1 (0.1 RMSE) and a comparable result with other teams (0.3 CER) in task 2 which demonstrated the effectiveness of the proposed method.

引用

页码：100 / 105

页数：6

共 22 条

[1]

Bahdanau D, 2016, Arxiv, DOI arXiv:1409.0473

[2]

Foret P, 2021, Arxiv, DOI [arXiv:2010.01412, DOI 10.48550/ARXIV.2010.01412]

[3] Single Shot Text Detector with Regional Attention [J].

He, Pan ;

Huang, Weilin ;

He, Tong ;

Zhu, Qile ;

Qiao, Yu ;

Li, Xiaolin .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :3066-3074

[4]

Denk TI, 2019, Arxiv, DOI arXiv:1909.04948

[5]

Katti AR, 2018, Arxiv, DOI arXiv:1809.08799

[6] Rotation-sensitive Regression for Oriented Scene Text Detection [J].

Liao, Minghui ;

Zhu, Zhen ;

Shi, Baoguang ;

Xia, Gui-song ;

Bai, Xiang .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :5909-5918

[7]

Liao MH, 2017, AAAI CONF ARTIF INTE, P4161

[8] Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection [J].

Liu, Yuliang ;

Jin, Lianwen .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :3454-3461

[9]

Long J, 2015, PROC CVPR IEEE, P3431, DOI 10.1109/CVPR.2015.7298965

[10]

Palm Rasmus Berg, 2019, 2019 International Conference on Document Analysis and Recognition (ICDAR). Proceedings, P329, DOI 10.1109/ICDAR.2019.00060

← 1 2 3 →