Important new developments in Arabographic Optical Character Recognition (OCR)

Benjamin Kiessling; Matthew Thomas Miller; Maxim G. Romanov; Sarah Bowen Savant

Important new developments in Arabographic Optical Character Recognition (OCR)

Benjamin Kiessling
, Matthew Thomas Miller
, Maxim G. Romanov
, Sarah Bowen Savant

Institute for the Study of Muslim Civilisations, UK

Research output: Contribution to journal › Article

Abstract

The Open Islamicate Texts Initiative (OpenITI) team building on the foundational open-source OCR work of the Leipzig University (LU) Alexander von Humboldt Chair for Digital Humanities—has achieved Optical Character Recognition (OCR) accuracy rates for printed classical Arabic-script texts in the high nineties. These numbers are based on our tests of seven different Arabic-script texts of varying quality and typefaces, totaling over 7,000 lines(~400 pages, 87,000 words; see Table 1 for full details). These accuracy rates not only represent a distinct improvement over the actual 2 accuracy rates of the various proprietary OCR options for printed classical Arabic-script texts, but, equally important, they are produced using an open-source OCR software called Kraken (developed by Benjamin Kiessling, LU)

Original language	Undefined/Unknown
Journal	Al-Usur al-Wusta: The Journal of Middle East Medievalists
Publication status	Published - 1 Jan 2017

Access to Document

http://ecommons.aku.edu/uk_ismc_faculty_publications/3

Cite this

@article{1fb93a81a3454500a742c8f0ad6bd1c0,

title = "Important new developments in Arabographic Optical Character Recognition (OCR)",

abstract = "The Open Islamicate Texts Initiative (OpenITI) team building on the foundational open-source OCR work of the Leipzig University (LU) Alexander von Humboldt Chair for Digital Humanities—has achieved Optical Character Recognition (OCR) accuracy rates for printed classical Arabic-script texts in the high nineties. These numbers are based on our tests of seven different Arabic-script texts of varying quality and typefaces, totaling over 7,000 lines(\textasciitilde{}400 pages, 87,000 words; see Table 1 for full details). These accuracy rates not only represent a distinct improvement over the actual 2 accuracy rates of the various proprietary OCR options for printed classical Arabic-script texts, but, equally important, they are produced using an open-source OCR software called Kraken (developed by Benjamin Kiessling, LU)",

author = "Benjamin Kiessling and \{Thomas Miller\}, Matthew and \{G. Romanov\}, Maxim and Savant, \{Sarah Bowen\}",

year = "2017",

month = jan,

day = "1",

language = "Undefined/Unknown",

journal = "Al-Usur al-Wusta: The Journal of Middle East Medievalists",

}

TY - JOUR

T1 - Important new developments in Arabographic Optical Character Recognition (OCR)

AU - Kiessling, Benjamin

AU - Thomas Miller, Matthew

AU - G. Romanov, Maxim

AU - Savant, Sarah Bowen

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The Open Islamicate Texts Initiative (OpenITI) team building on the foundational open-source OCR work of the Leipzig University (LU) Alexander von Humboldt Chair for Digital Humanities—has achieved Optical Character Recognition (OCR) accuracy rates for printed classical Arabic-script texts in the high nineties. These numbers are based on our tests of seven different Arabic-script texts of varying quality and typefaces, totaling over 7,000 lines(~400 pages, 87,000 words; see Table 1 for full details). These accuracy rates not only represent a distinct improvement over the actual 2 accuracy rates of the various proprietary OCR options for printed classical Arabic-script texts, but, equally important, they are produced using an open-source OCR software called Kraken (developed by Benjamin Kiessling, LU)

AB - The Open Islamicate Texts Initiative (OpenITI) team building on the foundational open-source OCR work of the Leipzig University (LU) Alexander von Humboldt Chair for Digital Humanities—has achieved Optical Character Recognition (OCR) accuracy rates for printed classical Arabic-script texts in the high nineties. These numbers are based on our tests of seven different Arabic-script texts of varying quality and typefaces, totaling over 7,000 lines(~400 pages, 87,000 words; see Table 1 for full details). These accuracy rates not only represent a distinct improvement over the actual 2 accuracy rates of the various proprietary OCR options for printed classical Arabic-script texts, but, equally important, they are produced using an open-source OCR software called Kraken (developed by Benjamin Kiessling, LU)

M3 - Article

JO - Al-Usur al-Wusta: The Journal of Middle East Medievalists

JF - Al-Usur al-Wusta: The Journal of Middle East Medievalists

ER -