Digitization Best Practices [Poster]

Abstract

This project involved performing tests and documenting results to determine best practices for digitizing older print documents. The digitization process is complicated, especially when original documents exhibit non-standard fonts and are faded. Tests focused on solutions to improve high quality scanning, increase OCR accuracy, and efficiently use embedded metadata. Results are summarized. From the test results on the right sides, we know that when we plan to digitize documents, we should balance Quantity and Quality based on our expectation, and then make final decision for the digitization process.