4 February 2013 Post processing with first- and second-order hidden Markov models
Author Affiliations +
Abstract
In this paper, we present the implementation and evaluation of first order and second order Hidden Markov Models to identify and correct OCR errors in the post processing of books. Our experiments show that the first order model approximately corrects 10% of the errors with 100% precision, while the second order model corrects a higher percentage of errors with much lower precision.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kazem Taghva, Srijana Poudel, Spandana Malreddy, "Post processing with first- and second-order hidden Markov models", Proc. SPIE 8658, Document Recognition and Retrieval XX, 865814 (4 February 2013); doi: 10.1117/12.2006500; https://doi.org/10.1117/12.2006500
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Analyzing machine noise for real time maintenance
Proceedings of SPIE (February 08 2017)
Retaining document format in OCR
Proceedings of SPIE (March 23 1994)
Automated geodata analysis and metadata generation
Proceedings of SPIE (March 12 2002)
Document image representation using XML technologies
Proceedings of SPIE (December 18 2001)

Back to Top