Panel on Optical Character Recognition

Today’s scholars expect Optical Character Recognition (OCR) of texts in library collections.   Despite expectations that all texts are equally discoverable, we know that countless handwritten manuscripts and documents in non-Roman fonts have neither been OCR’ed nor transcribed.   Three esteemed Harvard colleagues will discuss OCR projects that promise to open up vast quantities of knowledge to digital researchers.

• Sharon Tai, Deputy Editor at SHARIAsource will talk about Arabic OCR.
• Donald Sturgeon, a postdoctoral fellow at the Fairbank Center of Chinese Studies, will tell us about his work with Chinese texts.
• Amy Benson, Librarian/Archivist for Digital Projects at Schlesinger Library, will share how they aim to make handwriting searchable.

Join us for what is sure to be an informative discussion as our panelists share both the successes and challenges of their work.