Year of Publication


Document Type





Computer Science

First Advisor

W. Brent Seales


Recent large-scale document digitization initiatives have created new modes of access to modern library collections with the development of new hardware and software technologies. Most commonly, these digitization projects focus on accurately scanning bound texts, some reaching an efficiency of more than one million volumes per year. While vast digital collections are changing the way users access texts, current scanning paradigms can not handle many non-standard materials. Documentation forms such as manuscripts, scrolls, codices, deteriorated film, epigraphy, and rock art all hold a wealth of human knowledge in physical forms not accessible by standard book scanning technologies. This great omission motivates the development of new technology, presented by this thesis, that is not-only effective with deteriorated bound works, damaged manuscripts, and disintegrating photonegatives but also easily utilized by non-technical staff. First, a novel point light source calibration technique is presented that can be performed by library staff. Then, a photometric correction technique which uses known illumination and surface properties to remove shading distortions in deteriorated document images can be automatically applied. To complete the restoration process, a geometric correction is applied. Also unique to this work is the development of an image-based uncalibrated document scanner that utilizes the transmissivity of document substrates. This scanner extracts intrinsic document color information from one or both sides of a document. Simultaneously, the document shape is estimated to obtain distortion information. Lastly, this thesis provides a restoration framework for damaged photographic negatives that corrects photometric and geometric distortions. Current restoration techniques for the discussed form of negatives require physical manipulation to the photograph. The novel acquisition and restoration system presented here provides the first known solution to digitize and restore deteriorated photographic negatives without damaging the original negative in any way. This thesis work develops new methods of document scanning and restoration suitable for wide-scale deployment. By creating easy to access technologies, library staff can implement their own scanning initiatives and large-scale scanning projects can expand their current document-sets.