We present an Information Customization framework, which offers a unique hybrid of Adaptive Hypermedia and Constraint Satisfaction methods. IC is being modelled as a constraint sa...
—We present an OCR-driven writer identification algorithm in this paper. Our algorithm learns writer-specific characteristics more precisely from explicit character alignment usi...
We propose an approach to restore severely degraded
document images using a probabilistic context model. Un-
like traditional approaches that use previously learned
prior models...
Jyotirmoy Banerjee, Anoop M. Namboodiri, C. V. Jaw...
It is common for libraries to provide public access to historical and ancient document image collections. It is common for such document images to require specialized processing i...
This paper investigates the pre-conditions for successful combination of document representations formed from structural markup for the task of known-item search. As this task is ...