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.
@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}
}