Skip to main content
Article
Cryptogram decoding for optical character recognition
University of Massachusetts - Amherst Technical Report (2006)
  • Gary Huang, University of Massachusetts - Amherst
  • Erik G Learned-Miller, University of Massachusetts - Amherst
  • Andrew McCallum, University of Massachusetts - Amherst
Abstract

OCR systems for printed documents typically require large numbers of font styles and character models to work well. When given an unseen font, performance degrades even in the absence of noise. In this paper, we perform OCR in an unsupervised fashion without using any character models by using a cryptogram decoding algorithm. We present results on real and artificial OCR data.

Disciplines
Publication Date
August, 2006
Publisher Statement
doi: 10.1109/ICDAR.2007.4378705
Citation Information
Gary Huang, Erik G Learned-Miller and Andrew McCallum. "Cryptogram decoding for optical character recognition" University of Massachusetts - Amherst Technical Report Vol. 06 Iss. 45 (2006)
Available at: http://works.bepress.com/andrew_mccallum/34/