Post processing with first- and second-order hidden Markov models
Kazem Taghva, Srijana Poudel, Spandana Malreddy · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2013
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.