Word-Based Correction for Retrieval of Arabic OCR Degraded Documents

Walid Magdy; Kareem Darwish

doi:10.1007/11880561_17

Word-Based Correction for Retrieval of Arabic OCR Degraded Documents

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

Abstract / Description of output

Arabic documents that are available only in print continue to be ubiquitous and they can be scanned and subsequently OCR’ed to ease their retrieval. This paper explores the effect of word-based OCR correction on the effectiveness of retrieving Arabic OCR documents using different index terms. The OCR correction uses an improved character segment based noisy channel model and is tested on real and synthetic OCR degradation. Results show that the effect of OCR correction depends on the length of the index term used and that indexing using short n-grams is perhaps superior to word-based error correction. The results are potentially applicable to other languages.

Original language	English
Title of host publication	String Processing and Information Retrieval
Subtitle of host publication	13th International Conference, SPIRE 2006, Glasgow, UK, October 11-13, 2006, Proceedings
Publisher	Springer
Pages	205-216
Number of pages	12
ISBN (Electronic)	978-3-540-45775-6
ISBN (Print)	978-3-540-45774-9
DOIs	https://doi.org/10.1007/11880561_17
Publication status	Published - 2006

Publication series

Name	Lecture Notes in Computer Science (LNCS)
Publisher	Springer Berlin Heidelberg
Volume	4209
ISSN (Print)	0302-9743

Access to Document

10.1007/11880561_17

http://link.springer.com/chapter/10.1007%2F11880561_17

Cite this

@inproceedings{e06cb43147dc420d827bef309583cd83,

title = "Word-Based Correction for Retrieval of Arabic OCR Degraded Documents",

abstract = "Arabic documents that are available only in print continue to be ubiquitous and they can be scanned and subsequently OCR{\textquoteright}ed to ease their retrieval. This paper explores the effect of word-based OCR correction on the effectiveness of retrieving Arabic OCR documents using different index terms. The OCR correction uses an improved character segment based noisy channel model and is tested on real and synthetic OCR degradation. Results show that the effect of OCR correction depends on the length of the index term used and that indexing using short n-grams is perhaps superior to word-based error correction. The results are potentially applicable to other languages.",

author = "Walid Magdy and Kareem Darwish",

year = "2006",

doi = "10.1007/11880561_17",

language = "English",

isbn = "978-3-540-45774-9",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer",

pages = "205--216",

booktitle = "String Processing and Information Retrieval",

address = "United Kingdom",

}

Word-Based Correction for Retrieval of Arabic OCR Degraded Documents. / Magdy, Walid; Darwish, Kareem.
String Processing and Information Retrieval: 13th International Conference, SPIRE 2006, Glasgow, UK, October 11-13, 2006, Proceedings. Springer, 2006. p. 205-216 (Lecture Notes in Computer Science (LNCS); Vol. 4209).

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

TY - GEN

T1 - Word-Based Correction for Retrieval of Arabic OCR Degraded Documents

AU - Magdy, Walid

AU - Darwish, Kareem

PY - 2006

Y1 - 2006

N2 - Arabic documents that are available only in print continue to be ubiquitous and they can be scanned and subsequently OCR’ed to ease their retrieval. This paper explores the effect of word-based OCR correction on the effectiveness of retrieving Arabic OCR documents using different index terms. The OCR correction uses an improved character segment based noisy channel model and is tested on real and synthetic OCR degradation. Results show that the effect of OCR correction depends on the length of the index term used and that indexing using short n-grams is perhaps superior to word-based error correction. The results are potentially applicable to other languages.

AB - Arabic documents that are available only in print continue to be ubiquitous and they can be scanned and subsequently OCR’ed to ease their retrieval. This paper explores the effect of word-based OCR correction on the effectiveness of retrieving Arabic OCR documents using different index terms. The OCR correction uses an improved character segment based noisy channel model and is tested on real and synthetic OCR degradation. Results show that the effect of OCR correction depends on the length of the index term used and that indexing using short n-grams is perhaps superior to word-based error correction. The results are potentially applicable to other languages.

U2 - 10.1007/11880561_17

DO - 10.1007/11880561_17

M3 - Conference contribution

SN - 978-3-540-45774-9

T3 - Lecture Notes in Computer Science (LNCS)

SP - 205

EP - 216

BT - String Processing and Information Retrieval

PB - Springer

ER -

Word-Based Correction for Retrieval of Arabic OCR Degraded Documents

Abstract / Description of output

Publication series

Access to Document

Fingerprint

Cite this