Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms

Jiayi Zhang; Yue Liu

doi:10.1145/3611450.3611473

Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms

Jiayi Zhang, Yue Liu

Faculty of Applied Sciences

Macao Polytechnic University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The courier industry in China has grown quickly due to the rise of online shopping. However, courier notes can unavoidably become smudged or damaged during the delivery process, making it difficult to read the printed Chinese address information or recognize the barcodes. To solve this problem, this paper proposes an end-to-end solution to recognize damaged Chinese addresses: the CRNN model is trained for address recognition for damaged Chinese courier orders using a large Chinese address dataset generated via data augmentation and manual collection. And an address association algorithm is proposed to reduce the recognition errors at the provincial and municipal levels of the addresses. By applying this algorithm, the final accuracy is increased by 2% to 98.7%.

Original language	English
Title of host publication	Conference Proceedings - 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023
Publisher	Association for Computing Machinery
Pages	158-163
Number of pages	6
ISBN (Electronic)	9798400707605
DOIs	https://doi.org/10.1145/3611450.3611473
Publication status	Published - 21 Jul 2023
Event	3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023 - Beijing, China Duration: 21 Jul 2023 → 23 Jul 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023
Country/Territory	China
City	Beijing
Period	21/07/23 → 23/07/23

Keywords

CRNN
Chinese Address Dataset Generation
Chinese Address Recognition
Deep Learning

Access to Document

10.1145/3611450.3611473

Cite this

Zhang, J., & Liu, Y. (2023). Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms. In Conference Proceedings - 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023 (pp. 158-163). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3611450.3611473

@inproceedings{1e865e742f154ce58754cf0fac4a8bf3,

title = "Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms",

abstract = "The courier industry in China has grown quickly due to the rise of online shopping. However, courier notes can unavoidably become smudged or damaged during the delivery process, making it difficult to read the printed Chinese address information or recognize the barcodes. To solve this problem, this paper proposes an end-to-end solution to recognize damaged Chinese addresses: the CRNN model is trained for address recognition for damaged Chinese courier orders using a large Chinese address dataset generated via data augmentation and manual collection. And an address association algorithm is proposed to reduce the recognition errors at the provincial and municipal levels of the addresses. By applying this algorithm, the final accuracy is increased by 2% to 98.7%.",

keywords = "CRNN, Chinese Address Dataset Generation, Chinese Address Recognition, Deep Learning",

author = "Jiayi Zhang and Yue Liu",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023 ; Conference date: 21-07-2023 Through 23-07-2023",

year = "2023",

month = jul,

day = "21",

doi = "10.1145/3611450.3611473",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "158--163",

booktitle = "Conference Proceedings - 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023",

}

Zhang, J & Liu, Y 2023, Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms. in Conference Proceedings - 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 158-163, 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023, Beijing, China, 21/07/23. https://doi.org/10.1145/3611450.3611473

Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms. / Zhang, Jiayi; Liu, Yue.
Conference Proceedings - 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023. Association for Computing Machinery, 2023. p. 158-163 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms

AU - Zhang, Jiayi

AU - Liu, Yue

PY - 2023/7/21

Y1 - 2023/7/21

N2 - The courier industry in China has grown quickly due to the rise of online shopping. However, courier notes can unavoidably become smudged or damaged during the delivery process, making it difficult to read the printed Chinese address information or recognize the barcodes. To solve this problem, this paper proposes an end-to-end solution to recognize damaged Chinese addresses: the CRNN model is trained for address recognition for damaged Chinese courier orders using a large Chinese address dataset generated via data augmentation and manual collection. And an address association algorithm is proposed to reduce the recognition errors at the provincial and municipal levels of the addresses. By applying this algorithm, the final accuracy is increased by 2% to 98.7%.

AB - The courier industry in China has grown quickly due to the rise of online shopping. However, courier notes can unavoidably become smudged or damaged during the delivery process, making it difficult to read the printed Chinese address information or recognize the barcodes. To solve this problem, this paper proposes an end-to-end solution to recognize damaged Chinese addresses: the CRNN model is trained for address recognition for damaged Chinese courier orders using a large Chinese address dataset generated via data augmentation and manual collection. And an address association algorithm is proposed to reduce the recognition errors at the provincial and municipal levels of the addresses. By applying this algorithm, the final accuracy is increased by 2% to 98.7%.

KW - CRNN

KW - Chinese Address Dataset Generation

KW - Chinese Address Recognition

KW - Deep Learning

UR - http://www.scopus.com/inward/record.url?scp=85171257805&partnerID=8YFLogxK

U2 - 10.1145/3611450.3611473

DO - 10.1145/3611450.3611473

M3 - Conference contribution

AN - SCOPUS:85171257805

T3 - ACM International Conference Proceeding Series

SP - 158

EP - 163

BT - Conference Proceedings - 2023 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023

PB - Association for Computing Machinery

T2 - 3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023

Y2 - 21 July 2023 through 23 July 2023

ER -

Deep Learning-based End-to-End Address Recognition Solution on Chinese Courier Order Forms

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this