Building recognition systems for historical documents is a difficult task. Especially, when it comes to medieval scripts. The complexity is mainly affected by the poor quality and...
This paper describes the current state of RUgle, a system for classifying and indexing papers made available on the World Wide Web, in a domain-independent and universal manner. B...
Image anchor templates are used in document image analysis for document classification, data localization, and other tasks. Current tools allow human operators to mark out small s...
In this paper, we report on the design and implementation of a stemmer for the Farsi language. The results of our evaluation on a small Farsi document collection shows a signific...
We consider the problem of evaluating retrieval systems using a limited number of relevance judgments. Recent work has demonstrated that one can accurately estimate average precis...