An e-lesson is comprised of a "body" and a "view". The body is the actual content of the e-lesson and the assumption is that it is an html document. The view i...
We describe an approach to unsupervised high-accuracy recognition of the textual contents of an entire book using fully automatic mutual-entropy-based model adaptation. Given imag...
Many document-based applications, including popular Web browsers, email viewers, and word processors, have a ‘Find on this Page’ feature that allows a user to find every occur...
Kevyn Collins-Thompson, Charles Schweizer, Susan T...
This paper introduces a multifont classification scheme to help recognition of multifont and multisize characters. It uses typographical attributes such as ascenders, descenders a...
The paper presents the Position Specific Posterior Lattice (PSPL), a novel lossy representation of automatic speech recognition lattices that naturally lends itself to efficient ...