OCR-Enhanced Digital Asset Management System

Prototype Design and Construction

Abstract

Digitization initiatives has become increasingly prominent for libraries and information centers and aligned to this is the increase in the use of digital asset management systems to store the product of these initiatives. However, the fundamental purpose and objective for information today is more than just storing and preserving but also providing access. Since these are large amounts of documents, potential alternatives to providing access to these materials aside from manual data entry process such as indexing and cataloging, is explored. In this area, the potential of Optical Character Recognition (OCR) mechanisms is gaining prominence as the tool can process large number of documents and provide automated text recognition in high speed. Leveraging on this machine potential, this paper demonstrates the design and construction of a digital asset management system and the application of an open-source OCR mechanism to create a functional and adaptive system that can manage digital assets and retrieve information from these contents.