Hidden markov model based handwriting/calligraphy generation

Details Hidden markov model based handwriting/calligraphy generation Hidden markov model based handwriting/calligraphy generation

2011-07-19

2011-07-19

Werner, Brian (Department: 2624)

Image analysis

Learning systems

Trainable classifiers or pattern recognizers

C382S186000, C382S187000

Reexamination Certificate

active

07983478

ABSTRACT:
An exemplary method for handwritten character generation includes receiving one or more characters and, for the one or more received characters, generating handwritten characters using Hidden Markov Models trained for generating handwritten characters. In such a method the trained Hidden Markov Models can be adapted using a technique such as a maximum a posterior technique, a maximum likelihood linear regression technique or an Eigen-space technique.

REFERENCES:
patent: 5459809 (1995-10-01), Kim et al.
patent: 5588073 (1996-12-01), Lee et al.
patent: 5636291 (1997-06-01), Bellegarda et al.
patent: 5644652 (1997-07-01), Bellegarda et al.
patent: 5768423 (1998-06-01), Aref et al.
patent: 5812698 (1998-09-01), Platt et al.
patent: 5854855 (1998-12-01), Errico et al.
patent: 5920647 (1999-07-01), Nowlan et al.
patent: 6084985 (2000-07-01), Dolfing et al.
patent: 6956969 (2005-10-01), Loudon et al.
patent: 7054510 (2006-05-01), Milner
patent: 7227993 (2007-06-01), Xu et al.
patent: 7697002 (2010-04-01), McCall et al.
patent: 2004/0148577 (2004-07-01), Xu et al.
Chen, et al., “Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network”, available at least as early as May 4, 2007, at <<http://ieeexplore.ieee.org/iel1/34/7215/00291449.pdf?isNumber= >>, IEEE, vol. 16, No. 5, May 1994, pp. 481-496.
Makhoul, et al., On-Line Cursive Handwriting Recognition Using Hidden Markov Models and Statistical Grammars, available at least as early as May 4, 2007, at <<http://delivery.acm.org/10.1145/1080000/1075912/p432-makhoul.pdf?key1=1075912&key2=6459528711&coll=GUIDE&dl=GUIDE&CFID=17929888&CFTOKEN=43573113>>, pp. 432-436.
Tokuno, et al., “Context-Dependent Substroke Model for HMM-based On-line Handwriting Recognition”, availbale at least as early as May 4, 2007, at <<http://www.cstr.ed.ac.uk/downloads/publications/2002/Tokuno2002IWFHR.pdf>>, IWFHR, Aug. 2002, pp. 78-83.
PCT Search Report for PCT Application No. PCT/US2008/072833, mailed Jan. 29, 2009 (10 pages).
Sin, “An HMM-based Statistical Framework For Modeling On-line Cursive Script”, PhD thesis, Korea Advanced Institute of Science & Technology, Feb. 1995, 197 pages.
Sin, et al., “Hangul Character Generation using Hidden Markov Models”, Journal(B) of Korean Institue of Information Scientists and Engineers, Jan. 1997, vol. 24, No. 1, 11 pages.

Affiliated with

Also associated with

Rating

Hidden markov model based handwriting/calligraphy generation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Hidden markov model based handwriting/calligraphy generation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hidden markov model based handwriting/calligraphy generation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2698752