System and method for automatic handwriting recognition with a w

Image analysis – Pattern recognition – Unconstrained handwriting

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382187, 382228, G06K 918

Patent

active

056446527

ABSTRACT:
An automatic handwriting recognition system wherein each written (chirographic) manifestation of each character is represented by a statistical model (called a hidden Markov model). The system implements a method which entails sampling a pool of independent writers and deriving a hidden Markov model for each particular character (allograph) which is independent of a particular writer. The HMMs are used to derive a chirographic label alphabet which is independent of each writer. This is accomplished during what is described as the training phase of the system. The alphabet is constructed using supervised techniques. That is, the alphabet is constructed using information learned in the training phase to adjust the result according to a statistical algorithm (such as a Viterbi alignment) to arrive at a cost efficient recognition tool. Once such an alphabet is constructed a new set of HMMs can be defined which more accurately reflects parameter typing across writers. The system recognizes handwriting by applying an efficient hierarchical decoding strategy which employs a fast match and a detailed match function, thereby making the recognition cost effective.

REFERENCES:
patent: 4491960 (1985-01-01), Brown
patent: 4525860 (1985-07-01), Boivie
patent: 4653107 (1987-03-01), Shojima et al.
patent: 4718103 (1988-01-01), Shojima et al.
patent: 4731857 (1988-03-01), Tappert
patent: 5005205 (1991-04-01), Ellozy et al.
patent: 5023918 (1991-06-01), Lipscomb
patent: 5038382 (1991-08-01), Lipscomb
patent: 5075896 (1991-12-01), Wilcox et al.
patent: 5199077 (1993-03-01), Wilcox et al.
patent: 5343537 (1994-08-01), Bellegarda et al.
patent: 5392363 (1995-02-01), Fujisaki et al.
patent: 5459809 (1995-10-01), Kim et al.
"Symbol Recognition System By Elastic Matching", J.M. Kurtzberg et al., IBM Technical Disc. Bulletin, vol. 24, No. 6, Nov. 1981.
"Isolated Word-Recognition Method", IBM Technical Disc. Bulletin, vol. 29, No, 4, Sep. 1986.
"Subsampled Prototypes and Weighted Clustering", IBM Technical Disc. Bulletin, vol. 29, No. 8 Jan. 1987.
"Recognition of Handwritten Word: First and Second Order Hidden Markov Model Based Approach", A. Kundu, et al., Pattern Recognition, vol. 22, No. 3, pp. 283-297, 1989.
"Probabilistic Neural Functions of Markov Chains (Neural HMMs)", IBM Technical Disc. Bulletin, vol. 33, No. 7, Dec. 1990.
"Iterative Scheme for the Maximum Mutual Information Training of Hidden Markov Models", IBM Technical Disc. Bulletin, vol. 33, No. 7, Dec. 1990.
"Maximum Mutual Information Training of Hidden Markov Models with Continuous Parameters", IBM Technical Disc. Bulletin, vol. 33, No. 7, Dec. 1990.

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

System and method for automatic handwriting recognition with a w does not yet have a rating. At this time, there are no reviews or comments for this patent.

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

Rate now

     

Profile ID: LFUS-PAI-O-604097

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