Yue Ma

Ink Matching of Cursive Chinese Handwritten Annotations

April 1, 1998
10:00 - 11:30 AM
422 Snell

Abstract

In this dissertation, we discuss the notion of treating electronic ink as "first class" data without attempting to recognize it and apply this concept in the annotating of documents. We illustrate the feasibility of entering and manipulating annotations in a pen-based document management system by discussing several user interface issues. We also discuss the underlined electronic ink matching scheme for the searching of annotations once they are entered into the system. Adapting from the "Learning by knowledge" paradigm, we propose a semantic matching network that applies semantics of Chinese language early in the process of ink matching. Preliminary experimental results show that the semantic matching is an encouraging and feasible idea in the searching of cursive Chinese handwritten annotations despite the informal and highly variable nature of Chinese handwriting.

Thesis Committee:
Prof. J.D. Crisman (advisor)
Prof. P. Wang (Advisor, College of Computer Science)
Prof. E.S. Manolakos
Prof. D.H. Brooks