A More Complete History of America: Developing Arabic OCR to tell the story of Arabs in America

FAIN: ZPA-283823-22

North Carolina State University (Raleigh, NC 27695-0001)
Akram Fouad Khater (Project Director: May 2021 to present)
Chau-Wai Wong (Co Project Director: February 2022 to present)

The hiring of a computer specialist and the addition of graduate and undergraduate student workers to finish developing OCR technology for Arabic text and handwriting that would enable a text searchable archive of historical Arab American sources at the Khayrallah Center for Lebanese Diaspora Studies (KCLDS). 

North Carolina State University seeks support to complete the development of a text searchable open source archive of historical Arab American newspapers, books and manuscripts, complete with interactive analytic capacity. This ongoing project was critically disrupted by Covid-19 at a time when demand for online archives and advanced search capability has exponentially increased. Creating this resource through the development of OCR for Arabic text and handwriting, and the digitization of materials will advance our center's mission by bringing to light the hidden history of 150 years of Arab immigration to the US, and Arab American cultural, economic and political contributions to America. This cutting edge tool, and the unprecedented research it makes possible, will allow scholars to tell the stories of a long under-represented community, its encounter with race in America, and how it helped change the American landscape through its presence and activism on various fronts.