Image analysis – Pattern recognition – On-line recognition of handwritten characters
Reexamination Certificate
2007-02-20
2007-02-20
Desire, Gregory (Department: 2624)
Image analysis
Pattern recognition
On-line recognition of handwritten characters
C365S189011, C365S230010, C382S186000, C382S209000, C382S227000, C382S229000, C704S231000, C706S020000, C706S021000
Reexamination Certificate
active
11050392
ABSTRACT:
In computerized recognition having multiple experts, a method and system is described that obtains an optimum value for an expert tuning parameter in a single pass over sample tuning data. Each tuning sample is applied to two experts, resulting in scores from which ranges of parameters that correct incorrect recognition errors without changing correct results for that sample are determined. To determine the range data for a given sample, the experts return scores for each prototype in a database, the scores separated into matching and non-matching scores. The matching and non-matching scores from each expert are compared, providing upper and lower bounds defining ranges. Maxima and minima histograms track upper and lower bound range data, respectively. An analysis of the histograms based on the full set of tuning samples provides the optimum value. For tuning multiple parameters, each parameter may be optimized by this method in isolation, and then iterated.
REFERENCES:
patent: 5644652 (1997-07-01), Bellegarda et al.
patent: 5896321 (1999-04-01), Miller et al.
patent: 5960101 (1999-09-01), Lo et al.
patent: 6035062 (2000-03-01), Takasu et al.
patent: 6122401 (2000-09-01), Nagao
patent: 6233354 (2001-05-01), Nakatani
patent: 6418239 (2002-07-01), Hullender et al.
patent: 6502082 (2002-12-01), Toyama et al.
patent: 6594393 (2003-07-01), Minka et al.
patent: 6671403 (2003-12-01), Takasu et al.
patent: 6804396 (2004-10-01), Higaki et al.
patent: 6826306 (2004-11-01), Lewis et al.
patent: 6879718 (2005-04-01), Hullender
patent: 6970877 (2005-11-01), Rowley et al.
patent: 6988107 (2006-01-01), Meek et al.
patent: 7003158 (2006-02-01), Bennett et al.
patent: 2005/0129313 (2005-06-01), Hullender
Cho, Sung-Bae, “Pattern Recognition with Neural Networks Combined by Genetic Algorithm,” Fuzzy Sets and Systems 103 (1999), pp. 339-347.
Yeung et al., “Neocognitron Based Handwriting Recognition System Performance Tuning Using Genetic Algorithm,” 1998 IEE International Conference on Systems, Man and Cybernetics, pp. 4228-4233.
Guyon et al., “Capacity Control in Linear Classifiers for Pattern Recognition,” IEEE Computer Society Press, 1 IAPR International Conference on Pattern Recognition, 1992, pp. 385-388.
Said et al., “A new Back-Propagation Learning Algorithm with Application to Unconstrained Handwritten Character Recognition,” World Congress on Neural Networks, vol. 2, 1995 International Neural Network Society Annual Meeting, pp. 217-221.
Desire Gregory
Microsoft Corporation
LandOfFree
Efficient method and system for determining parameters in... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Efficient method and system for determining parameters in..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Efficient method and system for determining parameters in... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3849691