Image analysis – Learning systems – Neural networks
Patent
1994-12-21
1999-06-15
Mancuso, Joseph
Image analysis
Learning systems
Neural networks
382228, G06K 962
Patent
active
059129867
ABSTRACT:
Apparatus, and an accompanying method, for use in, e.g., a neural network-based optical character recognition (OCR) system (5) for accurately classifying each individual character extracted from a string of characters, and specifically for generating a highly reliable confidence measure that would be used in deciding whether to accept or reject each classified character. Specifically, a confidence measure, associated with each output of, e.g., a neural classifier (165), is generated through use of all the neural activation output values. Each individual neural activation output provides information for a corresponding atomic hypothesis of an evidence function. This hypothesis is that a pattern belongs to a particular class. Each neural output is transformed (1650) through a pre-defined monotonic function into a degree of support in its associated evidence function. These degrees of support are then combined (1680, 1690) through an orthogonal sum to yield a single confidence measure associated with the specific classification then being produced by the neural classifier.
REFERENCES:
patent: 4918618 (1990-04-01), Tomlinson
patent: 4933977 (1990-06-01), Ohnishi et al.
patent: 5052043 (1991-09-01), Goborski
patent: 5105468 (1992-04-01), Guyon et al.
patent: 5119438 (1992-06-01), Ueda et al.
patent: 5131073 (1992-07-01), Euruta et al.
patent: 5151951 (1992-09-01), Ueda et al.
patent: 5155801 (1992-10-01), Lincoln
patent: 5214746 (1993-05-01), Fogel et al.
patent: 5239593 (1993-08-01), Wittner et al.
patent: 5245672 (1993-09-01), Wilson et al.
patent: 5299269 (1994-03-01), Gaborski et al.
patent: 5392594 (1995-02-01), Yoda
patent: 5465308 (1995-11-01), Hutcheson et al.
Barnett, Computational methods for a mathematical theory of evidence, 1981, pp. 868-875.
J.A. Barnett, "Computational Methods for a Mathematical Theory of Evidence", Proceedings of the Seventh International Joint Conferences on Artificial Intelligence, Vancouver, British Columbia, 1981, pp. 868-875.
R. Battiti et al., "Democracy in Neural Nets: Voting Schemes for Classification", Neural Networks, vol. 7, No. 4, 1994, pp. 691-707.
Y. Bengion et al., "Globally Trained Handwritten Word Recognizer using Spatial Representation, Covolutional Neural Netowrks and Hidden Markov Models", Proceedings of 1993 Confierence on Neural Information Processing Systems--Natural and Synthetic, Nov. 29-Dec. 2, 1993, Denver Colorado, pp. 937-944.
J. Bromely et al., "Improving Rejection Performance on Handwritten Digits by Training with `Rubbish`", Neural Computation, vol. 5, 1993 (367-370).
J. Daugman, "Complete Discrete 2-D Gabor Transforms by Neural Networks for Image Analysis and Compression", IEEE Transactions on Acoustics, Speech and Signal Processing, 1988, vol. 36, No. 7, pp. 1169-1179.
J.A. Freeman et al., Neural Networks--Algorithms, Applications and Programming Techniques, pp. 89-125 (1991: Addison-Welsey Publishing Company, Inc.).
A. Gupta et al., "An Integrated Architecture for Recognition of Totally Unconstrained Handwritten Numerals", International Journal of Pattern Recognition and Artificial Intelligence, 1993, vol. 7, No. 4, pp. 757-773.
J. Keeler et al., "A Self-Organizing Integrated Segmentation and Recognition Neural Net", appears in J.E. Moody et al. (eds.), Advances in Neural Information Processing Systems, 1992, vol. 4, pp. 496-503 (Morgan Kaufmann Publishers, San Mateo, California).
G. Martin et al., "Learning to See Where and What: Training a Net to Make Saccades and Recognize Handwritten Characters" (1993), appears in S.J. Hanson et al. (eds.), Advances in Neural Information Processing Systems, vol. 5, pp. 441-447 (Morgan Kaufmann Publ., San Mateo, CA).
D.E. Rumelhart et al., Parallel Distributed Processing, vol. 1, pp. 328-330 (1988, MIT Press).
G. Shafer, A Mathematical Theory of Evidences, (1976: Princeton University Press), specifically pp. 3-78.
A. Shustorovich, "A Subspace Projection Approach to Feature Extraction: The Two-Dimensional Gabor Transform for Character Recognition"appeared in Neural Networks, 1994, vol. 7, No. 8.
F.F. Soulie et al., "Multi-Modular Neural Network Architectures: Applications in Optical Character and Human Face Recognition", International Journal of Pattern Recognition and Artificial Intelligence, vol. 7, No. 4, 1993, pp. 721-755, specifically pp. 728-729.
Blish Nelson A.
Eastman Kodak Company
Johnson Timothy M.
Mancuso Joseph
Michaelson Peter L.
LandOfFree
Evidential confidence measure and rejection technique for use 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 Evidential confidence measure and rejection technique for use in, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Evidential confidence measure and rejection technique for use in will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-407920