Concurrent two-stage multi-network optical character recognition

Details Concurrent two-stage multi-network optical character recognition Concurrent two-stage multi-network optical character recognition

1995-11-20

1998-11-10

Couso, Jose L.

Image analysis

Pattern recognition

On-line recognition of handwritten characters

382159, 382224, 382156, G06K 900, G06K 962

Patent

active

058356339

ABSTRACT:
A multi-stage multi-network character recognition system decomposes the estimation of a posteriori probabilities into coarse-to-fine stages. Classification is then based on the estimated a posteriori probabilities. This classification process is especially suitable for the tasks that involve a large number of categories. The multi-network system is implemented in two stages: a soft pre-classifier and a bank of multiple specialized networks. The pre-classifier performs coarse evaluation of the input character, developing different probabilities that the input character falls into different predefined character groups. The bank of specialized networks, each corresponding to a single group of characters, performs fine evaluation of the input character, where each develops different probabilities that the input character represents each character in that specialized network's respective predefined character group. A network selector is employed to increase the system's efficiency by selectively invoking certain specialized networks selected, using a combination of prior external information and outputs of the pre-classifier. Relative to known single network or one-stage multiple network recognition systems, the invention provides improved recognition, accuracy, confidence measure, speed, and flexibility.

REFERENCES:
patent: 4180779 (1979-12-01), Hook et al.
patent: 4958377 (1990-09-01), Takahashi
patent: 5020117 (1991-05-01), Ooi et al.
patent: 5052043 (1991-09-01), Gaborski
patent: 5150424 (1992-09-01), Asuro
patent: 5166539 (1992-11-01), Uchimura et al.
patent: 5195169 (1993-03-01), Kamiya et al.
patent: 5212767 (1993-05-01), Higashino et al.
patent: 5214717 (1993-05-01), Kimura et al.
patent: 5237661 (1993-08-01), Kawamura et al.
patent: 5239594 (1993-08-01), Yoda
patent: 5239619 (1993-08-01), Takatori et al.
patent: 5248873 (1993-09-01), Allen et al.
patent: 5257342 (1993-10-01), Takatori et al.
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5303311 (1994-04-01), Epting et al.
patent: 5327522 (1994-07-01), Furuta et al.
patent: 5361311 (1994-11-01), Wilson
patent: 5361379 (1994-11-01), White
patent: 5544264 (1996-08-01), Bellegarda et al.
patent: 5596657 (1997-01-01), Choi
Fujisaki, et al., U.S. application No. 08/061,495, "Hybrid On-Line Handwriting Recognition And Optical Character Recognition System".
T. Mano, et al., "Automatic Character Image Sanitizing Method for Optical Character Recognition Data Setup", IBM Technical Disclosure Bulletin, vol. 37, No. 11, Nov. 1994, p. 277.
T. Mano, et al., "Hybrid Optical Character Recognition System with Neural Network and Template Matching Recognition Methods", IBM Technical Disclosure Bulletin, vol. 37, No. 11, Nov. 1994, p. 275.
A. R. Rawson, "Application of Artificial Neural Networks to Fixed-Font Character Recognition", IBM Technical Disclosure Bulletin, vol. 34, No. 4A, Sep. 1991, pp. 469-472.
J. L. Huerta, "Anchor/Leveling Device for RISC 60000/Systems", IBM Technical Disclosure Bulletin, vol. 36, No. 12, Dec. 1993, p. 347.
E. Bellegarda, et al., "Fully Automatic Corpus Annotation Handwriting Recognition", IBM Technical Disclosure Bulletin, vol. 36, No. 12, Dec. 1993, pp. 343-345.
M.S. Narasimha, et al., "Partitioned Class Recognition By Computational Neural Network", IBM Technical Disclosure Bulletin, vol. 37, No. 11, Nov. 1994, pp. 7-9.
E. J. Bellegarda, et al., "Front-end Paradigm for On-Line Handwriting Recognition", IBM Technical Disclosure Bulletin, vol. 37, No. 02A, Feb. 1994, pp. 345-348.
R. T. Chien, et al., "Multilevel Adaptive Decision Techniques", IBM Technical Disclosure Bulletin, vol. 8, No. 4, Sep. 1965, pp. 580-582.
A. Takimoto, "An Optical Neuron Device Capable of Optical Parallel Operations and All-Optical Neural Networks", Electronics and Communications in Japan, Part 2, vol. 76, No. 10, 1993, pp. 1-9.
W. Robinson, et al., "Character Recognition Using Novel Optoelectronic Neural Network", SPIE, vol. 1902, Nonlinear Image Processing IV (1993), pp. 305-317.
T. Marek, "Analysis of Parallel Implementations of an Artificial Neural Network on SIMD Systems", SPIE, vol. 1709 Applications of Artificial Neural Networks III (1992), pp. 664-676.
H. Takahashi, "Neural Network Architectures for Rotated Character Recognition", 11th IAPR International Conference on Pattern Recognition, vol. II, Conference B: Pattern Recognition Methodology and Systems, The Hague, Netherlands, Aug. 30-Sep. 3, 1992, IEEE 1992, pp. 623-626.
B. Boser, "An Analog Neural Network Processor and Its Application to High-Speed Character Recognition", pp. I-415 -I-420, International Joint Conference on Neural Networks, vol. I, Jul. 8-12, 1991, Seattle, WA.
Y. Kimura, "Distorted Handwritten Kanji Character Pattern Recognition by a Learning Algorithm Minimizing Output Variation", pp. I-103 -I-106, International Joint Conference on Neural Networks, vol. I, Jul. 8-12, 1991, Seattle, WA.
B. White, "The Digi-Neocognitron: A Digital Neocognitron Neural Network Model for VLSI", IEEE Transactions on Neural Networks, Jan. 1992, vol. 3, No. 1, pp. 73-85.
D. Choi, "High Speed Character Recognition by Multiprocessor System", Journal of The Korean Institute of Telematics and Electronics, vol. 30-B, No. 2, Feb. 1993. (Korean -partial English language translation only).
W. You-shou, et al. "An Experimental System of Printed Chinese Character Recognition", Acta Electronica Sinica (China), vol. 15, No. 5, pp. 1-7. (Chinese -partial English language translation only).
K. Wong, et al., "Document Analysis System", 6th International Conference on Pattern Recognition, vol. I, IEEE 1992, pp. 496-500.
G. Dimauro, et al., "Integration of a Structural Features-Based Preclassifier and a Man-Machine Interactive Classifier for a Fast Multi-Stroke Character Recognition", 11th IAPR International Conference D: Architectures for Vision and Pattern Recognition, IEEE 1992, pp. 190-194.
M.D. Richard, et al, "Neural Network Classifiers Estimate Bayesian Posteriori Probabilities", Neural Computation, 3:461-483 (1991).
H. Takahaski, "A Neural Net OCR Using Geometrical and Zonal-Pattern Features", Proceedings of 1st International Conference on Document Analysis and Recognition, pp. 821-828 (1991).
R.G. Casey, et al., "Experience in Segmenting and Classifying the Nist Data Base", Proceedings of International Workshop on Frontiers of Handwriting (1991), pp. 1-15.
D.E. Rumelhart, et al., "Parallel Distributed Processing: Exploration in the Microstructure of Cognition", vol. 1-2, M.I.T. Press (1986), pp. 319-362.
R.A. Wilkinson, et al., "The First Census Optical Character Recognition System Conference", U.S. Department of Commerce, NISTIR 4912 (1992).

Affiliated with

Also associated with

Rating

Concurrent two-stage multi-network optical character recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Concurrent two-stage multi-network optical character recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Concurrent two-stage multi-network optical character recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1525692