Optical character recognition with fast training neural network

Huei Yung Lin; Chin Yu Hsu

doi:10.1109/ICIT.2016.7474973

Optical character recognition with fast training neural network

Huei Yung Lin
, Chin Yu Hsu

Department of Computer Science and Information Engineering

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

7 Scopus citations

Abstract

Optical character recognition has been extensively investigated in the past few years. Many existing techniques are able to provide high recognition rate, but at the cost of long training time. In this work, we present a neural network based approach to reduce the training time while maintain the high recognition rate. The main idea is to perform a preprocessing stage to partition the training data prior to the training stage. A multi-stage approach is then used to deal with various types of input source. Our experiments on real image datasets have demonstrated that the balance between the training time and recognition time can be achieved using the proposed method.

Original language	English
Title of host publication	Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1458-1461
Number of pages	4
ISBN (Electronic)	9781467380751
DOIs	https://doi.org/10.1109/ICIT.2016.7474973
State	Published - 19 May 2016
Event	IEEE International Conference on Industrial Technology, ICIT 2016 - Taipei, Taiwan Duration: 14 Mar 2016 → 17 Mar 2016

Publication series

Name	Proceedings of the IEEE International Conference on Industrial Technology
Volume	2016-May

Conference

Conference	IEEE International Conference on Industrial Technology, ICIT 2016
Country/Territory	Taiwan
City	Taipei
Period	14/03/16 → 17/03/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Access to Document

10.1109/ICIT.2016.7474973

Cite this

Lin, H. Y., & Hsu, C. Y. (2016). Optical character recognition with fast training neural network. In Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016 (pp. 1458-1461). Article 7474973 (Proceedings of the IEEE International Conference on Industrial Technology; Vol. 2016-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIT.2016.7474973

@inproceedings{ac67750961834d4f8bf916e79f7799e2,

title = "Optical character recognition with fast training neural network",

abstract = "Optical character recognition has been extensively investigated in the past few years. Many existing techniques are able to provide high recognition rate, but at the cost of long training time. In this work, we present a neural network based approach to reduce the training time while maintain the high recognition rate. The main idea is to perform a preprocessing stage to partition the training data prior to the training stage. A multi-stage approach is then used to deal with various types of input source. Our experiments on real image datasets have demonstrated that the balance between the training time and recognition time can be achieved using the proposed method.",

author = "Lin, \{Huei Yung\} and Hsu, \{Chin Yu\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; IEEE International Conference on Industrial Technology, ICIT 2016 ; Conference date: 14-03-2016 Through 17-03-2016",

year = "2016",

month = may,

day = "19",

doi = "10.1109/ICIT.2016.7474973",

language = "???core.languages.en\_GB???",

series = "Proceedings of the IEEE International Conference on Industrial Technology",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1458--1461",

booktitle = "Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016",

}

Lin, HY & Hsu, CY 2016, Optical character recognition with fast training neural network. in Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016., 7474973, Proceedings of the IEEE International Conference on Industrial Technology, vol. 2016-May, Institute of Electrical and Electronics Engineers Inc., pp. 1458-1461, IEEE International Conference on Industrial Technology, ICIT 2016, Taipei, Taiwan, 14/03/16. https://doi.org/10.1109/ICIT.2016.7474973

Optical character recognition with fast training neural network. / Lin, Huei Yung; Hsu, Chin Yu.
Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1458-1461 7474973 (Proceedings of the IEEE International Conference on Industrial Technology; Vol. 2016-May).

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

TY - GEN

T1 - Optical character recognition with fast training neural network

AU - Lin, Huei Yung

AU - Hsu, Chin Yu

PY - 2016/5/19

Y1 - 2016/5/19

N2 - Optical character recognition has been extensively investigated in the past few years. Many existing techniques are able to provide high recognition rate, but at the cost of long training time. In this work, we present a neural network based approach to reduce the training time while maintain the high recognition rate. The main idea is to perform a preprocessing stage to partition the training data prior to the training stage. A multi-stage approach is then used to deal with various types of input source. Our experiments on real image datasets have demonstrated that the balance between the training time and recognition time can be achieved using the proposed method.

AB - Optical character recognition has been extensively investigated in the past few years. Many existing techniques are able to provide high recognition rate, but at the cost of long training time. In this work, we present a neural network based approach to reduce the training time while maintain the high recognition rate. The main idea is to perform a preprocessing stage to partition the training data prior to the training stage. A multi-stage approach is then used to deal with various types of input source. Our experiments on real image datasets have demonstrated that the balance between the training time and recognition time can be achieved using the proposed method.

UR - https://www.scopus.com/pages/publications/84974603509

U2 - 10.1109/ICIT.2016.7474973

DO - 10.1109/ICIT.2016.7474973

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84974603509

T3 - Proceedings of the IEEE International Conference on Industrial Technology

SP - 1458

EP - 1461

BT - Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Industrial Technology, ICIT 2016

Y2 - 14 March 2016 through 17 March 2016

ER -

Optical character recognition with fast training neural network

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this