Adaptive OCR for books

Image analysis – Pattern recognition – Limited to specially coded – human-readable characters

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C382S185000, C382S186000, C358S001110

Reexamination Certificate

active

07627177

ABSTRACT:
A system is presented for scanning entire books or document all at once using an adaptive process where the book or document has known fonts and unknown fonts. The known fonts are processed through a verification system where sure words and error words are determined. Both the sure words and error words are sent to OCR training where they are re-OCR'ed and repeatedly verified until they meet a predetermined quality criteria. Characters or words not meeting the predetermined quality criteria receive additional OCR training until all the characters and words pass the predetermined quality criteria. Unknown fonts are scanned and clustered together by shape. Outliers in the shapes are manually keyed-in. Those symbols that are manually classified go to OCR training and then to the known type optimization process.

REFERENCES:
patent: 4944022 (1990-07-01), Yasujima et al.
patent: 5359673 (1994-10-01), de La Beaujardiere
patent: 5583949 (1996-12-01), Smith et al.
patent: 5625711 (1997-04-01), Nicholson et al.
patent: 5754671 (1998-05-01), Higgins et al.
patent: 5917941 (1999-06-01), Webb et al.
patent: 5933525 (1999-08-01), Makhoul et al.
patent: 5966460 (1999-10-01), Porter et al.
patent: 6028970 (2000-02-01), DiPiazza et al.
patent: 6154579 (2000-11-01), Goldberg
patent: 6295543 (2001-09-01), Block et al.
patent: 6327385 (2001-12-01), Kamitani
patent: 6385350 (2002-05-01), Nicholson et al.
patent: 6678415 (2004-01-01), Popat et al.
patent: 6701023 (2004-03-01), Gaither et al.
patent: 6738518 (2004-05-01), Minka et al.
patent: 7092870 (2006-08-01), Chen et al.
patent: 7106905 (2006-09-01), Simske
patent: 7236632 (2007-06-01), Erol et al.
patent: 7240062 (2007-07-01), Andersen et al.
patent: 2002/0076111 (2002-06-01), Dance et al.
patent: 2002/0122594 (2002-09-01), Goldberg et al.
patent: 2003/0152269 (2003-08-01), Bourbakis et al.
patent: 2004/0223197 (2004-11-01), Ohta et al.
patent: 2005/0276519 (2005-12-01), Kitora et al.
patent: 2006/0215937 (2006-09-01), Snapp
patent: 2008/0063279 (2008-03-01), Vincent et al.
patent: 2008/0144977 (2008-06-01), Meyer et al.
IOCR: An Intelligent Optical Character Reader, Leung et al., The Chinese University of Hong Kong, IEEE 1989.
IBM TDB, N9, 02-92, pp. 256-260 entitled “Multi-Font Recognition Method Using a Layered Template Dictionary” by S. Katoh et al., 1992.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Adaptive OCR for books does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Adaptive OCR for books, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive OCR for books will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-4116900

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.