Automated recognition of characters using optical filtering with

Details Automated recognition of characters using optical filtering with Automated recognition of characters using optical filtering with

1992-05-14

1994-12-06

Couso, Yon J.

Image analysis

Histogram processing

For setting a threshold

382 10, 382 32, 382 42, G06K 962

Patent

active

053718089

ABSTRACT:
A method and apparatus is described for recognition of hand printed characters using maximum uncertainty--minimum variance (MUMV) functions, such as Gabor functions, implemented by optical elements. A set of optical elements having varying optical density corresponding to a set of two-dimensional MUMV functions is generated. A pattern of illumination responsive to the image of the character to be identified is simultaneously transmitted through each of the optical elements implementing the MUMV functions. The amount of light transmitted through each of the elements is measured, providing a transmission coefficient. Such transmission coefficients are used as a set of inputs to a neural network, such that the inputs to the neural network are a set of transmission coefficients resulting from transmission of light corresponding to a character to be identified through a complete set of optical elements implementing a set of two-dimensional MUMV functions. The neural network calculates weighted sums of the transmission coefficients. The neural network may be implemented as a network of resistors connected between input nodes, intermediate nodes, and output nodes. The output node having the highest voltage identifies the character to be identified.

REFERENCES:
patent: 3879605 (1975-04-01), Carl et al.
patent: 4082431 (1978-04-01), Ward, III
patent: 4590608 (1986-05-01), Chen et al.
patent: 4854669 (1989-08-01), Birnbach et al.
patent: 4959870 (1990-09-01), Tachikawa
patent: 4989257 (1991-01-01), Horowitz
patent: 5014327 (1991-05-01), Potter et al.
patent: 5047968 (1991-09-01), Carrington et al.
patent: 5050220 (1991-09-01), Marsh et al.
patent: 5063602 (1991-11-01), Peppers et al.
patent: 5086483 (1992-02-01), Capps
Uncertainty relation for resolution in space, spatial frequency, and Orietion Optimized by Two-dimensional Visual Cortical Filters, pp. 1160-1169 Daugman, Havard University, J. Opt. Soc. AM. A/vol. 2 No. 7/ Jul. 1985.
Complete Discrete 2-D Gabor Transforms by Neural Networks for Image Analysis and Compression, Daugman, IEEE Transactions on Acoustics, Speech and Signal Processing vol. 36, No. 7, Jul. 1988, pp. 1169-1179.
Winner-Take-All Network of O(N) Complexity, Advances in New Information Processing Systems 1, Ed. D. S. Touretzky, 1989, pp. 703-711.
Karhunen Loeve Feature Extraction For Neural Handwritten Character Recognition, Patrick J. Grother, Image Recognition Group NISI, SPIE, vol. 1709, Apr. 1992, pp. 1-11.
Training Feed Forward Neural Networks Using Conjugate Gradients, Grother et al, U.S. Department of Commerce NISI NISTIR 4776, Feb. 1992, pp. 1-22.
Massively Parelel Implementation of Character Recognition Systems Garris et al, U.S. Department of Commerce NISI, NISTIR4750, Jan. 1992, pp. 1-12.
Self-Organizing Neural Network Character Recognition on a Massively Parallel Computer, Wilson et al, NIST, International Joint Conference on Neural Networks Proceeding, II, pp. 325-329, Jun. 1990, San Diego, Calif.
Analysis of a Biologically Motivated Neural Network for Character Recognition, Garris et al, NIST, Proceedings: Analysis of Neural Network Applications, ACM Press, George Mason University, May 1991, pp. 160-175.
Methods for Enhancing Neural Network Handwritten Character Recognition, Carris et al, NIST, International Joint Conference on Neural Networks, vol. 1, IEEE, Seattle, Jul. 1991, pp. I-695-I-700.

Affiliated with

Also associated with

Rating

Automated recognition of characters using optical filtering with does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Automated recognition of characters using optical filtering with, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated recognition of characters using optical filtering with will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-220751