What is Recovered Memories?

“Recovered Memories” is the first step to textually digitizing documents housed in the Air Force archive at Maxwell Air Force Base, Alabama. Using a semi-curated collection of Vietnam-war era papers—the Project CHECO reports—as a pilot, the project leverages “crowd-sourced” volunteers to either transcribe these decades-old documents directly, or correct existing text files generated by optical character recognition (OCR) software, to near 100 percent accuracy.

Why is this important?

Textual digitization means converting image-based documents - such as the scanned in and preprocessed CHECO reports used here - into actual text, not just a picture of that text. Digital historians will use the final products for data mining, the production of e-books, or the creation of a data-heavy website illuminating the Air Force’s role in the Vietnam War.

This project also supports doctoral level research in Information and Interaction Design at the University of Baltimore. Researchers will use the data gathered by this application to evaluate the efficacy of the crowd, i.e. what attributes make a volunteer better suited to the task of textual digitization. Factors measured will include age, gender, education level, and group affiliation, among others.

We need your help!

You can support our efforts by signing up to transcribe or correct declassified Project CHECO reports.

Get Started