Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach

Yi Wang; Chen Wang; Bo Chen

doi:10.1007/978-981-33-6318-2_51

Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach

Yi Wang^*
, Chen Wang
, Bo Chen

^*Corresponding author for this work

Plymouth Business School

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings published in a book › peer-review

Abstract

Huge volumes of antient handwriting documents which has a wealth of information and knowledge, in forms of books, manuscripts or scanned images have been existing in various libraries, offices, museums and different archives all over the world. However, in order to further usage of these raw materials, they need to be transformed into a digital form that would allow the users to read, index, brows and query or even to understand further easily. It is a challenge to maintain and understand the paper-based documents. In this paper, some deep learning based approaches are presented to deal with this sort of documents. This paper also proposed a framework of such a system and future directions for the upcoming researchers in the field.

Original language	English
Title of host publication	Advanced Manufacturing and Automation X
Editors	Yi Wang, Kristian Martinsen, Tao Yu, Kesheng Wang
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	408-415
Number of pages	8
ISBN (Print)	9789813363175
DOIs	https://doi.org/10.1007/978-981-33-6318-2_51
Publication status	Published - 2021
Event	10th International Workshop of Advanced Manufacturing and Automation, IWAMA 2020 - Zhanjiang, China Duration: 12 Oct 2020 → 13 Oct 2020

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	737
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	10th International Workshop of Advanced Manufacturing and Automation, IWAMA 2020
Country/Territory	China
City	Zhanjiang
Period	12/10/20 → 13/10/20

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Keywords

Ancient document
CNN
DBN
Deep learning
Handwriting recognition
RNN

Access to Document

10.1007/978-981-33-6318-2_51

Cite this

Wang, Y., Wang, C., & Chen, B. (2021). Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach. In Y. Wang, K. Martinsen, T. Yu, & K. Wang (Eds.), Advanced Manufacturing and Automation X (pp. 408-415). (Lecture Notes in Electrical Engineering; Vol. 737). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-33-6318-2_51

@inproceedings{a988ba93ced04112b06aac2e399de4f8,

title = "Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach",

abstract = "Huge volumes of antient handwriting documents which has a wealth of information and knowledge, in forms of books, manuscripts or scanned images have been existing in various libraries, offices, museums and different archives all over the world. However, in order to further usage of these raw materials, they need to be transformed into a digital form that would allow the users to read, index, brows and query or even to understand further easily. It is a challenge to maintain and understand the paper-based documents. In this paper, some deep learning based approaches are presented to deal with this sort of documents. This paper also proposed a framework of such a system and future directions for the upcoming researchers in the field.",

keywords = "Ancient document, CNN, DBN, Deep learning, Handwriting recognition, RNN",

author = "Yi Wang and Chen Wang and Bo Chen",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 10th International Workshop of Advanced Manufacturing and Automation, IWAMA 2020 ; Conference date: 12-10-2020 Through 13-10-2020",

year = "2021",

doi = "10.1007/978-981-33-6318-2\_51",

language = "English",

isbn = "9789813363175",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "408--415",

editor = "Yi Wang and Kristian Martinsen and Tao Yu and Kesheng Wang",

booktitle = "Advanced Manufacturing and Automation X",

address = "Germany",

}

Wang, Y, Wang, C & Chen, B 2021, Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach. in Y Wang, K Martinsen, T Yu & K Wang (eds), Advanced Manufacturing and Automation X. Lecture Notes in Electrical Engineering, vol. 737, Springer Science and Business Media Deutschland GmbH, pp. 408-415, 10th International Workshop of Advanced Manufacturing and Automation, IWAMA 2020, Zhanjiang, China, 12/10/20. https://doi.org/10.1007/978-981-33-6318-2_51

Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach. / Wang, Yi; Wang, Chen; Chen, Bo.
Advanced Manufacturing and Automation X. ed. / Yi Wang; Kristian Martinsen; Tao Yu; Kesheng Wang. Springer Science and Business Media Deutschland GmbH, 2021. p. 408-415 (Lecture Notes in Electrical Engineering; Vol. 737).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings published in a book › peer-review

TY - GEN

T1 - Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach

AU - Wang, Yi

AU - Wang, Chen

AU - Chen, Bo

PY - 2021

Y1 - 2021

N2 - Huge volumes of antient handwriting documents which has a wealth of information and knowledge, in forms of books, manuscripts or scanned images have been existing in various libraries, offices, museums and different archives all over the world. However, in order to further usage of these raw materials, they need to be transformed into a digital form that would allow the users to read, index, brows and query or even to understand further easily. It is a challenge to maintain and understand the paper-based documents. In this paper, some deep learning based approaches are presented to deal with this sort of documents. This paper also proposed a framework of such a system and future directions for the upcoming researchers in the field.

AB - Huge volumes of antient handwriting documents which has a wealth of information and knowledge, in forms of books, manuscripts or scanned images have been existing in various libraries, offices, museums and different archives all over the world. However, in order to further usage of these raw materials, they need to be transformed into a digital form that would allow the users to read, index, brows and query or even to understand further easily. It is a challenge to maintain and understand the paper-based documents. In this paper, some deep learning based approaches are presented to deal with this sort of documents. This paper also proposed a framework of such a system and future directions for the upcoming researchers in the field.

KW - Ancient document

KW - CNN

KW - DBN

KW - Deep learning

KW - Handwriting recognition

KW - RNN

UR - https://www.scopus.com/pages/publications/85101853944

U2 - 10.1007/978-981-33-6318-2_51

DO - 10.1007/978-981-33-6318-2_51

M3 - Conference proceedings published in a book

AN - SCOPUS:85101853944

SN - 9789813363175

T3 - Lecture Notes in Electrical Engineering

SP - 408

EP - 415

BT - Advanced Manufacturing and Automation X

A2 - Wang, Yi

A2 - Martinsen, Kristian

A2 - Yu, Tao

A2 - Wang, Kesheng

PB - Springer Science and Business Media Deutschland GmbH

T2 - 10th International Workshop of Advanced Manufacturing and Automation, IWAMA 2020

Y2 - 12 October 2020 through 13 October 2020

ER -

Research Challenges in Off-Line Ancient Handwriting Recognition – A Deep Learning Approach

Abstract

Publication series

Conference

ASJC Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this