Abstract

POSTER PAPER. Automatic indexing and searching in handwritten medical forms is a very important task. It is very challenging due to the poor image quality and the consequent low OCR performance. We describe a handwritten document retrieval system that improves the existing techniques in two respects. First, we present a Markov Random Fields based preprocessing algorithm that improves the image quality and OCR performance. Second, we improve the existing retrieval techniques by utilizing the OCR probabilities and language model into the term-weight scheme.

Date

May 18, 2008

Authors

Huaigu Cao, Venu Govindaraju

Book

Proceedings of the 2008 international conference on Digital government research

Pages

371-372