Combiner for improving handwriting recognition

Details Combiner for improving handwriting recognition Combiner for improving handwriting recognition

2006-05-31

2010-10-19

Lu, Tom Y (Department: 2624)

Image analysis

Pattern recognition

Unconstrained handwriting

C382S181000, C382S185000, C382S187000, C382S156000, C382S157000, C706S015000, C706S019000, C706S020000, C706S025000

Reexamination Certificate

active

07817857

ABSTRACT:
Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.

REFERENCES:
patent: 4024500 (1977-05-01), Herbst et al.
patent: 4760604 (1988-07-01), Cooper et al.
patent: 5315667 (1994-05-01), Fujisaki et al.
patent: 5319721 (1994-06-01), Chefalas et al.
patent: 5438631 (1995-08-01), Dai
patent: 5854855 (1998-12-01), Errico et al.
patent: 6111985 (2000-08-01), Hullender et al.
patent: 6493464 (2002-12-01), Hawkins et al.
patent: 6603881 (2003-08-01), Perrone et al.
patent: 7031530 (2006-04-01), Driggs et al.
patent: 2004/0148577 (2004-07-01), Xu et al.
patent: 2005/0005240 (2005-01-01), Reynar et al.
patent: 2005/0069203 (2005-03-01), Khomo
patent: 2005/0100214 (2005-05-01), Zhang et al.
patent: 2005/0100217 (2005-05-01), Abdulkader et al.
patent: 2005/0251744 (2005-11-01), Brill et al.
patent: 11-167606 (1999-06-01), None
Aksela (“Handwritten Character Recognition: a palm-top implementation and adaptive committee experiments”, Helsinki University of Technology—thesis, 2000, p. 90-96).
Zimmerman et al. (“Parsing N-best lists of handwritten sentences”, Proceedings ICDAR, 2003, p. 1-5).
Bunke (“Recognition of cursive roman handwriting—past, present and future”, Proceedings ICDAR, 2003, p. 1-12).
Bunke (“Recognition of cursive roman handwriting—past, present and future”, Proceedings ICDAR, 2003, p. 1-12.
International Search Report PCT/US2007/010872, Dated Oct. 30, 2007, pp. 1-7.
“Handwriting”, http://www.penreader.com/technologies/Handwriting.html.
Senior et al., “An Off-Line Cursive Handwriting Recognition System”, Mar. 1998, vol. No. 20, http://www.cs.berkeley.edu/˜daf/appsem/Handwriting/papers/00667887.pdf.
Chen et al., “FreeStyle Handwriting Recognition”, http://www.ceresoft.com/freestyle.html, Nov. 8, 2002.
“CalliGrapher 8.2 for Pocket PCs”, http://www.phatware.com/calligrapher/index.html.

Affiliated with

Also associated with

Rating

Combiner for improving handwriting recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4235018