Personal tools
You are here: Home Publications Correcting Broken Characters in the Recognition of Historical Printed Documents

Correcting Broken Characters in the Recognition of Historical Printed Documents

last modified 2007-03-13

Droettboom, M., 2003

In: Proceedings of the 3rd ACM/IEEE-CS Joint Conference on Digital Libraries. Edited by IEEE..

Abstract:
This paper presents a new technique for dealing with broken characters, one of the major challenges in the optical character recognition (OCR) of degraded historical printed documents. A technique based on graph combinatorics is used to rejoin the appropriate connected components. It has been applied to real data with successful results.

URL:
http://dkc.jhu.edu/gamera/papers/droettboom_broken_characters.pdf
« March 2017 »
Su Mo Tu We Th Fr Sa
1234
567891011
12131415161718
19202122232425
262728293031