OCR in Ottoman

Thanks to recent advances in image processing and information technologies, Optical Character Recognition (OCR) has become applicable on a wide range of written materials. OCR enables both printed and manuscript texts to be recorded on computer in readable and treatable formats. IRCICA made an authentic contribution in this field by developing the OCR for Ottoman language which was lacking. Systems existing for Arabic and Persian did not allow treatment of texts in Ottoman. For this reason, IRCICA worked as of 2011 on developing an OCR for Ottoman which it put up as a unique software conform to international standards.

IRCICA obtained the Trademark Registration Certificate for OCR in Ottoman from the Turkish Patent Institute. With this system, it is possible to search words in books printed in Ottoman script, that is, in a voluminous body of literature produced during the period from the introduction of printing techniques to the Ottoman Empire in 1729 until the adoption of the Latin alphabet in Turkey in 1928. This material comprises works in Ottoman authored in all fields of sciences, culture, arts and history and printed with varying fonts at different printing houses.