Optical character recognition for typeset mathematics

Benjamin P. Berman; Richard J. Fateman

doi:10.1145/190347.190438

Optical character recognition for typeset mathematics

Benjamin P. Berman, Richard J. Fateman

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

19 Scopus citations

Abstract

There is a wealth of mathematical knowledge that could be potentially very useful in many computational applications, but is not available in electronic form. This knowledge comes in the form of mechanically typeset books and journals going back more than a hundred years. Besides these older sources, there are a great many current publications, filled with useful mathematical information, which are difficult if not impossible to obtain in electronic form. What we would like to do is extract character information from these documents, which could then be passed to higher-level parsing routines for further extraction of mathematical content (or any other useful 2-dimensional semantic content). Unfortunately, current commercial OCR (optical character recognition) software packages are quite unable to handle mathematical formulas, since their algorithms at all levels use heuristics developed for other document styles. We are concerned with the development of OCR methods that m-e able to handle this specialized task of mathematical expression recognition.

Original language	American English
Title of host publication	Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC 1994
Publisher	Association for Computing Machinery
Pages	348-353
Number of pages	6
ISBN (Electronic)	0897916387
DOIs	https://doi.org/10.1145/190347.190438
State	Published - 1 Aug 1994
Externally published	Yes
Event	1994 International Symposium on Symbolic and Algebraic Computation, ISSAC 1994 - Oxford, United Kingdom Duration: 20 Jul 1994 → 22 Jul 1994

Publication series

Name	Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC
Volume	Part F129423

Conference

Conference	1994 International Symposium on Symbolic and Algebraic Computation, ISSAC 1994
Country/Territory	United Kingdom
City	Oxford
Period	20/07/94 → 22/07/94

Bibliographical note

Funding Information:
*This work was supported in part by NSF Grant number CCR-9214963 and by NSF Infrastructure Grant number CDA-87227SS.

Publisher Copyright:
© 1994 ACM.

Access to Document

10.1145/190347.190438

Cite this

Berman, B. P., & Fateman, R. J. (1994). Optical character recognition for typeset mathematics. In Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC 1994 (pp. 348-353). (Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC; Vol. Part F129423). Association for Computing Machinery. https://doi.org/10.1145/190347.190438

@inproceedings{f9300fd746044ac692e78edb1f623bb0,

title = "Optical character recognition for typeset mathematics",

abstract = "There is a wealth of mathematical knowledge that could be potentially very useful in many computational applications, but is not available in electronic form. This knowledge comes in the form of mechanically typeset books and journals going back more than a hundred years. Besides these older sources, there are a great many current publications, filled with useful mathematical information, which are difficult if not impossible to obtain in electronic form. What we would like to do is extract character information from these documents, which could then be passed to higher-level parsing routines for further extraction of mathematical content (or any other useful 2-dimensional semantic content). Unfortunately, current commercial OCR (optical character recognition) software packages are quite unable to handle mathematical formulas, since their algorithms at all levels use heuristics developed for other document styles. We are concerned with the development of OCR methods that m-e able to handle this specialized task of mathematical expression recognition.",

author = "Berman, {Benjamin P.} and Fateman, {Richard J.}",

note = "Funding Information: *This work was supported in part by NSF Grant number CCR-9214963 and by NSF Infrastructure Grant number CDA-87227SS. Publisher Copyright: {\textcopyright} 1994 ACM.; 1994 International Symposium on Symbolic and Algebraic Computation, ISSAC 1994 ; Conference date: 20-07-1994 Through 22-07-1994",

year = "1994",

month = aug,

day = "1",

doi = "10.1145/190347.190438",

language = "American English",

series = "Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC",

publisher = "Association for Computing Machinery",

pages = "348--353",

booktitle = "Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC 1994",

}

Berman, BP & Fateman, RJ 1994, Optical character recognition for typeset mathematics. in Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC 1994. Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC, vol. Part F129423, Association for Computing Machinery, pp. 348-353, 1994 International Symposium on Symbolic and Algebraic Computation, ISSAC 1994, Oxford, United Kingdom, 20/07/94. https://doi.org/10.1145/190347.190438

Optical character recognition for typeset mathematics. / Berman, Benjamin P.; Fateman, Richard J.
Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC 1994. Association for Computing Machinery, 1994. p. 348-353 (Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC; Vol. Part F129423).

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

TY - GEN

T1 - Optical character recognition for typeset mathematics

AU - Berman, Benjamin P.

AU - Fateman, Richard J.

PY - 1994/8/1

Y1 - 1994/8/1

N2 - There is a wealth of mathematical knowledge that could be potentially very useful in many computational applications, but is not available in electronic form. This knowledge comes in the form of mechanically typeset books and journals going back more than a hundred years. Besides these older sources, there are a great many current publications, filled with useful mathematical information, which are difficult if not impossible to obtain in electronic form. What we would like to do is extract character information from these documents, which could then be passed to higher-level parsing routines for further extraction of mathematical content (or any other useful 2-dimensional semantic content). Unfortunately, current commercial OCR (optical character recognition) software packages are quite unable to handle mathematical formulas, since their algorithms at all levels use heuristics developed for other document styles. We are concerned with the development of OCR methods that m-e able to handle this specialized task of mathematical expression recognition.

AB - There is a wealth of mathematical knowledge that could be potentially very useful in many computational applications, but is not available in electronic form. This knowledge comes in the form of mechanically typeset books and journals going back more than a hundred years. Besides these older sources, there are a great many current publications, filled with useful mathematical information, which are difficult if not impossible to obtain in electronic form. What we would like to do is extract character information from these documents, which could then be passed to higher-level parsing routines for further extraction of mathematical content (or any other useful 2-dimensional semantic content). Unfortunately, current commercial OCR (optical character recognition) software packages are quite unable to handle mathematical formulas, since their algorithms at all levels use heuristics developed for other document styles. We are concerned with the development of OCR methods that m-e able to handle this specialized task of mathematical expression recognition.

UR - http://www.scopus.com/inward/record.url?scp=84931442262&partnerID=8YFLogxK

U2 - 10.1145/190347.190438

DO - 10.1145/190347.190438

M3 - Conference contribution

AN - SCOPUS:84931442262

T3 - Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC

SP - 348

EP - 353

BT - Proceedings of the International Symposium on Symbolic and Algebraic Computation, ISSAC 1994

PB - Association for Computing Machinery

T2 - 1994 International Symposium on Symbolic and Algebraic Computation, ISSAC 1994

Y2 - 20 July 1994 through 22 July 1994

ER -

Optical character recognition for typeset mathematics

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this