Cryptogram Decoding for OCR Using Numerization Strings

	This Article
	Subscribers, please Login Purchase article: $19 PDF RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by G. Huang Articles by E. Learned-Miller Articles by A. McCallum

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 1

Curitiba, Parana, Brazil

September 23-September 26

ISBN: 0-7695-2822-8

	ASCII Text	x
	G. Huang, E. Learned-Miller, A. McCallum, "Cryptogram Decoding for OCR Using Numerization Strings," Document Analysis and Recognition, International Conference on, vol. 1, pp. 208-212, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 1, 2007.

	BibTex	x
	@article{ 10.1109/ICDAR.2007.93, author = {G. Huang and E. Learned-Miller and A. McCallum}, title = {Cryptogram Decoding for OCR Using Numerization Strings}, journal ={Document Analysis and Recognition, International Conference on}, volume = {1}, year = {2007}, issn = {1520-5363}, pages = {208-212}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.2007.93}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Document Analysis and Recognition, International Conference on TI - Cryptogram Decoding for OCR Using Numerization Strings SN - 1520-5363 SP208 EP212 A1 - G. Huang, A1 - E. Learned-Miller, A1 - A. McCallum, PY - 2007 VL - 1 JA - Document Analysis and Recognition, International Conference on ER -

G. Huang, University of Massachuse

E. Learned-Miller, University of Massachuse

A. McCallum, University of Massachuse

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICDAR.2007.93

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 charac- ter models by using a cryptogram decoding algorithm. We present results on real and artificial OCR data.

Citation:

G. Huang, E. Learned-Miller, A. McCallum, "Cryptogram Decoding for OCR Using Numerization Strings," icdar, vol. 1, pp.208-212, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 1, 2007

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.