Article

Correcting broken characters in the recognition of historical printed documents

Author:

Michael DroettboomAuthors Info & Claims

JCDL '03: Proceedings of the 3rd ACM/IEEE-CS joint conference on Digital libraries

Pages 364 - 366

Published: 27 May 2003 Publication History

Get Access

Abstract

This paper presents a new technique for dealing with broken characters, one of the major challenges in the optical character recognition (OCR) of degraded historical printed documents. A technique based on graph combinatorics is used to rejoin the appropriate connected components. It has been applied to real data with successful results.

References

[1]

T. Cover, and P. Hart. 1967. Nearest neighbour pattern classification. IEEE Trans. on Inform. Theory. 13(1): 21--7.

Crossref

Google Scholar

[2]

M. Droettboom, K. MacMillan, I. Fujinaga, G. S. Choudhury, T. DiLauro, M. Patton, and T. Anderson. 2002. Using the Gamera framework for the recognition of cultural heritage materials. JCDL. 11--7.

Digital Library

Google Scholar

[3]

I. Fujinaga, B. Alphonce, B. Pennycook, and K. Hogan. 1991. Optical music recognition: Progress report. Int. Comp. Music Conf. 66--73.

Google Scholar

[4]

S. M. Harding, W. B. Croft, and C. Weir. 1997. Probabilistic retrieval of OCR degraded text using N-grams. Europ. Conf. on Dig. Libraries. 345--59.

Digital Library

Google Scholar

[5]

M. Kass, A. Witkin and D. Terzopolous. 1987. Snakes: Active contour models. Int. Conf. on Comp. Vision. 259--68.

Google Scholar

[6]

Statistical Accounts of Scotland. 1799. http://edina.ac.uk/statacc/

Google Scholar

[7]

Ø. D. Trier, and A. K. Jain. 1995. Goal-directed evaluation of binarization methods. IEEE Trans. on Pattern Analysis & Machine Intelligence. 17(12): 1191--201.

Digital Library

Google Scholar

Cited By

View all

Sharma SChoudhray SKumar B(2015)Recognition of Machine Printed Broken Oriya Characters Using Sift FeaturesProceedings of the Sixth International Conference on Computer and Communication Technology 201510.1145/2818567.2818587(106-109)Online publication date: 25-Sep-2015
https://dl.acm.org/doi/10.1145/2818567.2818587
Efron MJones GSheridan PKelly Dde Rijke MSakai T(2013)Query representation for cross-temporal information retrievalProceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval10.1145/2484028.2484054(383-392)Online publication date: 28-Jul-2013
https://dl.acm.org/doi/10.1145/2484028.2484054
Bar-Yosef IMokeichev AKedem KDinstein IEhrlich U(2009)Adaptive shape prior for recognition and variational segmentation of degraded historical charactersPattern Recognition10.1016/j.patcog.2008.10.00542:12(3348-3354)Online publication date: 1-Dec-2009
https://dl.acm.org/doi/10.1016/j.patcog.2008.10.005
Show More Cited By

Index Terms

Correcting broken characters in the recognition of historical printed documents
1. Applied computing
  1. Computers in other domains
    1. Digital libraries and archives
  2. Document management and text processing
    1. Document capture
      1. Optical character recognition
2. Information systems
  1. Information retrieval
    1. Document representation
      1. Document collection models
  2. Information systems applications
    1. Digital libraries and archives

Recommendations

Machine Recognition of Hand-Printed Chinese Characters

The recognition of Chinese characters has been an area of great interest for many years, and a large number of research papers and reports have already been published in this area. There are several major problems with Chinese character recognition: ...
Recognition of Machine Printed Broken Oriya Characters Using Sift Features
ICCCT '15: Proceedings of the Sixth International Conference on Computer and Communication Technology 2015

OCR for Indian scripts has been an active area of research for years. The fine printed documents can be recognized easily but the technology underperforms in case of degraded document images. In this paper a gradient based feature extraction technique ...
A knowledge-based recognition system for historical Mongolian documents

This paper proposes a knowledge-based system to recognize historical Mongolian documents in which the words exhibit remarkable variation and character overlapping. According to the characteristics of Mongolian word formation, the system combines a ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

JCDL '03: Proceedings of the 3rd ACM/IEEE-CS joint conference on Digital libraries

May 2003

393 pages

ISBN:0769519393

Conference Chair:
Lois Delcambre
Oregon Health & Science University
,
General Chair:
Geneva Henry
Rice University
,
Program Chair:
Catherine C. Marshall
Microsoft Corporation

Publisher

IEEE Computer Society

United States

Publication History

Published: 27 May 2003

Check for updates

Qualifiers

Article

Conference

JCDL03

Sponsor:

JCDL03: Joint Conference on Digital Libraries 2003

May 27 - 31, 2003

Texas, Houston

Acceptance Rates

JCDL '03 Paper Acceptance Rate 54 of 216 submissions, 25%;

Overall Acceptance Rate 415 of 1,482 submissions, 28%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
472
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 23 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Sharma SChoudhray SKumar B(2015)Recognition of Machine Printed Broken Oriya Characters Using Sift FeaturesProceedings of the Sixth International Conference on Computer and Communication Technology 201510.1145/2818567.2818587(106-109)Online publication date: 25-Sep-2015
https://dl.acm.org/doi/10.1145/2818567.2818587
Efron MJones GSheridan PKelly Dde Rijke MSakai T(2013)Query representation for cross-temporal information retrievalProceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval10.1145/2484028.2484054(383-392)Online publication date: 28-Jul-2013
https://dl.acm.org/doi/10.1145/2484028.2484054
Bar-Yosef IMokeichev AKedem KDinstein IEhrlich U(2009)Adaptive shape prior for recognition and variational segmentation of degraded historical charactersPattern Recognition10.1016/j.patcog.2008.10.00542:12(3348-3354)Online publication date: 1-Dec-2009
https://dl.acm.org/doi/10.1016/j.patcog.2008.10.005
Likforman-Sulem LSigelle M(2008)Recognition of degraded characters using dynamic Bayesian networksPattern Recognition10.1016/j.patcog.2008.03.02241:10(3092-3103)Online publication date: 1-Oct-2008
https://dl.acm.org/doi/10.1016/j.patcog.2008.03.022

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Machine Recognition of Hand-Printed Chinese Characters

Recognition of Machine Printed Broken Oriya Characters Using Sift Features

A knowledge-based recognition system for historical Mongolian documents