Creation of data resources and design of an evaluation test bed for Devanagari script recognition

S. Setlur; S. Kompalli; V. Ramanaprasad; V. Govindaraju

doi:10.1109/RIDE.2003.1249846

Creation of data resources and design of an evaluation test bed for Devanagari script recognition

S. Setlur
, S. Kompalli
, V. Ramanaprasad
, V. Govindaraju

University at Buffalo

SUNY Buffalo

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

15 Scopus citations

Abstract

The Indian subcontinent has a large number of languages, dialects, and scripts with the Devanagari script being the primary and most widely used of all the scripts. To date, much of the Devanagari optical character recognition (OCR) research has been restricted to a handful of groups. So, techniques have not yet been widely disseminated or evaluated independently and automated evaluation tools are currently not available for lack of a standard representation of ground-truth and result data. A key reason for the absence of sustained research efforts in off-line Devanagari OCR appears to be the paucity of data resources. Ground truthed data for words and characters, on-line dictionaries, corpora of text documents and reliable, standardized statistical analyses and evaluation tools are currently lacking. So, the creation of such data resources will undoubtedly provide a much needed fillip to researchers working on Devanagari OCR. This paper describes a National Science Foundation sponsored project under the International Digital Libraries program to create data resources that will facilitate development of Devanagari OCR technology and provide a standardized test bed and evaluation tools for Devanagari script recognition.

Original language	English
Title of host publication	Proceedings - 13th International Work Shop on Research Issues in Data Engineering
Subtitle of host publication	Multi-Lingual Information Management, RIDE-MLIM 2003
Editors	Rajeev Sangal, Bruce Croft
Publisher	IEEE Computer Society
Pages	55-61
Number of pages	7
ISBN (Electronic)	0780378687, 9780780378681
DOIs	https://doi.org/10.1109/RIDE.2003.1249846
State	Published - 2003
Event	13th International Workshop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003 - Hyderabad, India Duration: Mar 10 2003 → Mar 11 2003

Publication series

Name	Proceedings of the IEEE International Workshop on Research Issues in Data Engineering
Volume	2003-January

Conference

Conference	13th International Workshop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003
Country/Territory	India
City	Hyderabad
Period	03/10/03 → 03/11/03

Keywords

Character recognition
Dictionaries
Natural languages
Optical character recognition software
Shape
Software libraries
Statistical analysis
Testing
Text analysis
Text recognition

Access to Document

10.1109/RIDE.2003.1249846

Cite this

Setlur, S., Kompalli, S., Ramanaprasad, V., & Govindaraju, V. (2003). Creation of data resources and design of an evaluation test bed for Devanagari script recognition. In R. Sangal, & B. Croft (Eds.), Proceedings - 13th International Work Shop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003 (pp. 55-61). Article 1249846 (Proceedings of the IEEE International Workshop on Research Issues in Data Engineering; Vol. 2003-January). IEEE Computer Society. https://doi.org/10.1109/RIDE.2003.1249846

Setlur, S. ; Kompalli, S. ; Ramanaprasad, V. et al. / Creation of data resources and design of an evaluation test bed for Devanagari script recognition. Proceedings - 13th International Work Shop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003. editor / Rajeev Sangal ; Bruce Croft. IEEE Computer Society, 2003. pp. 55-61 (Proceedings of the IEEE International Workshop on Research Issues in Data Engineering).

@inproceedings{4c303a5cba28497aabcd954ff31efb9f,

title = "Creation of data resources and design of an evaluation test bed for Devanagari script recognition",

abstract = "The Indian subcontinent has a large number of languages, dialects, and scripts with the Devanagari script being the primary and most widely used of all the scripts. To date, much of the Devanagari optical character recognition (OCR) research has been restricted to a handful of groups. So, techniques have not yet been widely disseminated or evaluated independently and automated evaluation tools are currently not available for lack of a standard representation of ground-truth and result data. A key reason for the absence of sustained research efforts in off-line Devanagari OCR appears to be the paucity of data resources. Ground truthed data for words and characters, on-line dictionaries, corpora of text documents and reliable, standardized statistical analyses and evaluation tools are currently lacking. So, the creation of such data resources will undoubtedly provide a much needed fillip to researchers working on Devanagari OCR. This paper describes a National Science Foundation sponsored project under the International Digital Libraries program to create data resources that will facilitate development of Devanagari OCR technology and provide a standardized test bed and evaluation tools for Devanagari script recognition.",

keywords = "Character recognition, Dictionaries, Natural languages, Optical character recognition software, Shape, Software libraries, Statistical analysis, Testing, Text analysis, Text recognition",

author = "S. Setlur and S. Kompalli and V. Ramanaprasad and V. Govindaraju",

note = "Publisher Copyright: {\textcopyright} 2003 IEEE.; 13th International Workshop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003 ; Conference date: 10-03-2003 Through 11-03-2003",

year = "2003",

doi = "10.1109/RIDE.2003.1249846",

language = "English",

series = "Proceedings of the IEEE International Workshop on Research Issues in Data Engineering",

publisher = "IEEE Computer Society",

pages = "55--61",

editor = "Rajeev Sangal and Bruce Croft",

booktitle = "Proceedings - 13th International Work Shop on Research Issues in Data Engineering",

address = "United States",

}

Setlur, S, Kompalli, S, Ramanaprasad, V & Govindaraju, V 2003, Creation of data resources and design of an evaluation test bed for Devanagari script recognition. in R Sangal & B Croft (eds), Proceedings - 13th International Work Shop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003., 1249846, Proceedings of the IEEE International Workshop on Research Issues in Data Engineering, vol. 2003-January, IEEE Computer Society, pp. 55-61, 13th International Workshop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003, Hyderabad, India, 03/10/03. https://doi.org/10.1109/RIDE.2003.1249846

Creation of data resources and design of an evaluation test bed for Devanagari script recognition. / Setlur, S.; Kompalli, S.; Ramanaprasad, V. et al.
Proceedings - 13th International Work Shop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003. ed. / Rajeev Sangal; Bruce Croft. IEEE Computer Society, 2003. p. 55-61 1249846 (Proceedings of the IEEE International Workshop on Research Issues in Data Engineering; Vol. 2003-January).

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

TY - GEN

T1 - Creation of data resources and design of an evaluation test bed for Devanagari script recognition

AU - Setlur, S.

AU - Kompalli, S.

AU - Ramanaprasad, V.

AU - Govindaraju, V.

PY - 2003

Y1 - 2003

N2 - The Indian subcontinent has a large number of languages, dialects, and scripts with the Devanagari script being the primary and most widely used of all the scripts. To date, much of the Devanagari optical character recognition (OCR) research has been restricted to a handful of groups. So, techniques have not yet been widely disseminated or evaluated independently and automated evaluation tools are currently not available for lack of a standard representation of ground-truth and result data. A key reason for the absence of sustained research efforts in off-line Devanagari OCR appears to be the paucity of data resources. Ground truthed data for words and characters, on-line dictionaries, corpora of text documents and reliable, standardized statistical analyses and evaluation tools are currently lacking. So, the creation of such data resources will undoubtedly provide a much needed fillip to researchers working on Devanagari OCR. This paper describes a National Science Foundation sponsored project under the International Digital Libraries program to create data resources that will facilitate development of Devanagari OCR technology and provide a standardized test bed and evaluation tools for Devanagari script recognition.

AB - The Indian subcontinent has a large number of languages, dialects, and scripts with the Devanagari script being the primary and most widely used of all the scripts. To date, much of the Devanagari optical character recognition (OCR) research has been restricted to a handful of groups. So, techniques have not yet been widely disseminated or evaluated independently and automated evaluation tools are currently not available for lack of a standard representation of ground-truth and result data. A key reason for the absence of sustained research efforts in off-line Devanagari OCR appears to be the paucity of data resources. Ground truthed data for words and characters, on-line dictionaries, corpora of text documents and reliable, standardized statistical analyses and evaluation tools are currently lacking. So, the creation of such data resources will undoubtedly provide a much needed fillip to researchers working on Devanagari OCR. This paper describes a National Science Foundation sponsored project under the International Digital Libraries program to create data resources that will facilitate development of Devanagari OCR technology and provide a standardized test bed and evaluation tools for Devanagari script recognition.

KW - Character recognition

KW - Dictionaries

KW - Natural languages

KW - Optical character recognition software

KW - Shape

KW - Software libraries

KW - Statistical analysis

KW - Testing

KW - Text analysis

KW - Text recognition

UR - https://www.scopus.com/pages/publications/80054798729

U2 - 10.1109/RIDE.2003.1249846

DO - 10.1109/RIDE.2003.1249846

M3 - Conference contribution

T3 - Proceedings of the IEEE International Workshop on Research Issues in Data Engineering

SP - 55

EP - 61

BT - Proceedings - 13th International Work Shop on Research Issues in Data Engineering

A2 - Sangal, Rajeev

A2 - Croft, Bruce

PB - IEEE Computer Society

T2 - 13th International Workshop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003

Y2 - 10 March 2003 through 11 March 2003

ER -

Setlur S, Kompalli S, Ramanaprasad V, Govindaraju V. Creation of data resources and design of an evaluation test bed for Devanagari script recognition. In Sangal R, Croft B, editors, Proceedings - 13th International Work Shop on Research Issues in Data Engineering: Multi-Lingual Information Management, RIDE-MLIM 2003. IEEE Computer Society. 2003. p. 55-61. 1249846. (Proceedings of the IEEE International Workshop on Research Issues in Data Engineering). doi: 10.1109/RIDE.2003.1249846

Creation of data resources and design of an evaluation test bed for Devanagari script recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this