English

Important New Developments in Arabographic Optical Character Recognition (OCR)

Computer Vision and Pattern Recognition 2017-03-29 v1 Digital Libraries

Abstract

The OpenITI team has achieved Optical Character Recognition (OCR) accuracy rates for 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. These accuracy rates not only represent a distinct improvement over the actual accuracy rates of the various proprietary OCR options for classical Arabic-script texts, but, equally important, they are produced using an open-source OCR software, thus enabling us to make this Arabic-script OCR technology freely available to the broader Islamic, Persian, and Arabic Studies communities.

Keywords

Cite

@article{arxiv.1703.09550,
  title  = {Important New Developments in Arabographic Optical Character Recognition (OCR)},
  author = {Maxim Romanov and Matthew Thomas Miller and Sarah Bowen Savant and Benjamin Kiessling},
  journal= {arXiv preprint arXiv:1703.09550},
  year   = {2017}
}
R2 v1 2026-06-22T18:59:18.837Z