Nicholaos Bourbakis (Committee Chair), Soon Chung (Committee Member), S. Narayanan (Committee Member), Krishnaprasad Thirunarayan (Committee Member)
Doctor of Philosophy (PhD)
While mobile reading devices have been on the market and investigated by researchers in recent years, there is still work required to make these devices highly accessible to the visually impaired. A usability test with one such device revealed gaps in the current state of the art devices. These gaps focus mostly on the user interaction and his or her ability to quickly consume written reading material. In this dissertation a voice user interface (VUI) is presented that improves the ability of a blind user of a mobile reading device to interact with written material. The image processing techniques required to facilitate this interaction with a document image are also presented. Contributions of this research include a model of the VUI, which was validated by user tests of a prototype with visually impaired participants, a document image perspective correction technique, a document image dewarping technique, and a headline identification technique, among others. Three separate user tests with visually impaired participants were used to guide and validate the interaction research. The document image processing techniques, combined to form a document image processing pipeline, were tested on 25 document images. Comparative results from the user tests and processing of the document images are presented in this dissertation.
Department or Program
Department of Computer Science and Engineering
Year Degree Awarded
Copyright 2011, all rights reserved. This open access ETD is published by Wright State University and OhioLINK.