Image analysis – Pattern recognition – Context analysis or word recognition
Reexamination Certificate
2005-09-27
2005-09-27
Ahmed, Samir (Department: 2623)
Image analysis
Pattern recognition
Context analysis or word recognition
C358S462000
Reexamination Certificate
active
06950555
ABSTRACT:
In a combined holistic and analytic recognition system, the holistic recognition module will recognize an input word or phrase image by matching an input string of character features for the whole word or phrase against a string of prototype features for a plurality of reference words in a lexicon. This will yield a holistic answer list of recognized word or phrase candidates for the input word or phrase along with a confidence value for each answer on the list. At the same time based on each answer in the answer list, the holistic recognition modules will generate a list of character features and segment the character features into sets for each character in an answer. The analytical recognition module uses segmentation hypotheses from the segmented character feature sets to cut the image of the input string of characters into individual character images. A plurality of character images for the various segmentation hypotheses will be recognized to produce an analytical answer list having a plurality of word or phrase answers for the input word or phrase. Each analytic word answer will have a confidence value based on the combined confidence of recognizing each character. The holistic answer list and the analytic answer list will be examined to find the best answer from the two lists as the recognition of the input handwritten text.
REFERENCES:
patent: 5144683 (1992-09-01), Suzuki et al.
patent: 5287275 (1994-02-01), Kimura
patent: 5313527 (1994-05-01), Guberman et al.
patent: 5455872 (1995-10-01), Bradley
patent: 5832108 (1998-11-01), Fukita et al.
patent: 5987170 (1999-11-01), Yamamoto et al.
patent: 6041141 (2000-03-01), Yamamoto et al.
Chin et al. “Empirical design of a holistic verifier for automatic sorting of handwritten Singapore Postal Addresses”, Document Analysis and Recognition, 1999, pp. 733-736.
Casey et al. “A survey of methods and strategies in character segmentation”, Pattern Analysis and Machine Intelligence, IEEE, 1996, pp. 690-706.
Sherkat et al. “Whole word recognition in facsimile images”, Document Analysis and Recognition, 1999, pp. 547-550.
Madhvanath et al. “The role of holistic paradigms in handwritten word recognition”, Pattern Analysis and Machine Intelligence, 2001, pp. 149-164.
An Algorithm Toolbox for On-Line Cursive Script Recognition, Robert K. Powalka, Doctoral Thesis, ‘Online!’; Oct. 1995, pp. 1-286, Nottingham, UK; http://citeseer.nj.nec.com/rd/70348799%2C209471%2C1%2C0.25%2CDownload/http://citeseer.nj.nec.com/compress/0/papers/cs/8855/http:zSzzSzwww.doc.ntu.ac.ukzSz{inkdataSzrkpzSzthesis.main.ps.gz/an-algorithm-toolbox-for.ps.
A Multi-Classifier Combination Strategy for the Recognition of Handwritten Cursive Words, B. Plessis, et al.; Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on Tsukuba Science City, Japan, Oct. 20-22, 1993, Los Alamitos, CA, USA, IEEE Comput. Soc.; Oct. 20, 1993, pp. 642-645.
Serial Classifier Combination for Handwritten Word Recognition; S. Madhvanath, et al.; Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on Montreal, QUE., Canada Aug. 14-16, 1995, Los Alamitos, CA, USA, IEEE Comput. Soc., US; Aug. 14, 1995, pp. 911-914.
Methods of Combining Multiple Classifiers and Their Applications to Handwriting Recognition, L. Xu, et al., IEEE Transactions on Systems, Man and Cybernetics, IEEE Inc., New York, US, vol. 22, No. 3, May 1992, pp. 418-435, section III.A. Average Bayes Classifier.
Handwritten Word Recognition—The Approach Proved by Practice, Gregory Dzuba, Alexander Filatov, Dmitry Gershuny, Igor Kil; Parascript, LLC; www.parascript.com.
A Novel Learning Method by Structural Reduction of Dags for On-Line OCR Applications, I-Jong Lin and S.Y. Kung; Dept. of Electrical Engineering, Princeton University, Princeton, NJ.
Coding and Comparison of DAGs as a Novel Neural Structure with Applications to On-Line Handwriting Recognition; I-Jong Lin and S.Y. Kung, Princeton University, Princeton, NJ; www.ee-princeton.edu/˜ijonglin/spaces//spaces.html.
Check Amount Recognition Based on the Cross Validation of Courtesy and Legal Amount Fields; Gregory Dzuba, Alexander Filatov, Dmitry Gershuny, Igor Kil, Vadim Nikitin; Parascript, LLC.
Filatov Alexander
Kil Igor
Seregin Arseni
Ahmed Samir
Le Brian
Merchant & Gould P.C.
Parascript LLC
LandOfFree
Holistic-analytical recognition of handwritten text does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Holistic-analytical recognition of handwritten text, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Holistic-analytical recognition of handwritten text will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3397265