| | |
Summary: Word-Based Adaptive OCR for Historical Books
Vladimir Kluzner, Asaf Tzadok,
Yuval Shimony, Eugene Walach
IBM Corporation, Haifa Research Lab
{kvladi, asaf, yshimony, walach}@il.ibm.com
Apostolos Antonacopoulos
School of Computing, Science and Engineering
University of Salford
A.Antonacopoulos@primaresearch.org
Abstract
The aim of this work is to propose a new approach to
the recognition of historical texts by providing an adap-
tive mechanism that automatically tunes itself to a specific
book. The system is based on clustering together all the
similar words in a book/text and simultaneously handling
entire class. The paper describes the architecture of such
a system and new algorithms that have been developed for
robust word image comparison (including registration, opti-
cal flow based distortion compensation, and adaptive bina-
rization). Results for a large dataset are presented as well.
|
