Character and pattern recognition machine and method

Image analysis – Histogram processing – For setting a threshold

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382 7, 382 9, 382 30, 235379, G06K 946, G06K 900

Patent

active

048378429

ABSTRACT:
A pattern recognition system, particularly a handprint character recognition system in which electrical binary black/white "image" of one or more handprinted characters is formed and a plurality of centers of recognition (CORs) within said binary black/white images are selected as reference points for measuring the characteristic enclave of the black/white image immediately surrounding the CORs. A library of templates of said measurements around the CORs for a plurality of known exemplary character images is stored in a memory for comparison with corresponding measurements made around the CORs of images whose class is unknown to produce "template scores" proportional to the similarity of the enclaves of the known image to the enclaves measured by templates. The generic shape of a character is expressed as a "character equation" involving template scores developed on an unknown image, and each character equation is evaluated including comparing the values of such equations, and selecting the best value to determine the generic name of the unknown character.

REFERENCES:
patent: 3108254 (1963-10-01), Diamond
patent: 3142818 (1964-07-01), Holt
patent: 3164806 (1965-01-01), Rabinow
patent: 3178687 (1965-04-01), Perotto
patent: 3200373 (1965-08-01), Rabinow
patent: 3201751 (1965-08-01), Rabinow
patent: 3219974 (1965-11-01), Rabinow
patent: 3222650 (1965-12-01), Lazarus
patent: 3290650 (1966-12-01), Bailey, Jr. et al.
patent: 3303466 (1967-02-01), Holt
patent: 3348200 (1967-10-01), Ross
patent: 3500325 (1970-03-01), Greanians et al.
patent: 3517387 (1978-06-01), Andrews et al.
patent: 3519990 (1970-07-01), Holt
patent: 3521236 (1970-07-01), Parks et al.
patent: 3597731 (1971-08-01), Reitboack et al.
patent: 3609685 (1971-09-01), Deutsch
patent: 3626368 (1971-12-01), Lee
patent: 3651368 (1972-03-01), Holt
patent: 3766520 (1973-10-01), Patterson
patent: 3889234 (1975-06-01), Makihara et al.
patent: 3909785 (1975-09-01), Howells
patent: 3999161 (1976-12-01), Van Bilzem et al.
patent: 4047010 (1977-09-01), Perotto
patent: 4066998 (1978-01-01), Lidkea
patent: 4087788 (1978-05-01), Johannesson
patent: 4090223 (1978-05-01), Holt
patent: 4139869 (1979-02-01), Holt
patent: 4155072 (1979-05-01), Zawa
patent: 4163214 (1979-07-01), Zomori et al.
patent: 4193056 (1980-05-01), Morita et al.
patent: 4288779 (1981-09-01), Otsu et al.
patent: 4318083 (1982-03-01), Argyle
patent: 4365235 (1982-12-01), Greanias et al.
patent: 4395700 (1983-07-01), McCubbrey et al.
patent: 4398176 (1983-08-01), Dargel et al.
patent: 4414685 (1983-11-01), Sternberg
patent: 4415880 (1983-11-01), Scott
patent: 4461029 (1984-07-01), Van Bilzem et al.
patent: 4468808 (1984-08-01), Mori et al.
patent: 4491960 (1985-01-01), Brown
patent: 4525860 (1985-06-01), Boivie
patent: 4547898 (1985-10-01), Tsikos
patent: 4561106 (1985-12-01), Yoshida
patent: 4628532 (1986-12-01), Stone
Univ. of Texas, pp. 768-781, Kamangar et al., "Recognition of Handwritten Numbers Using a Multilayer . . .".
CGA-HBS, pp. 797-812, Gardin Du Boisdulier et al., "Topological Modelization of Handwritten Digits . . .".
Concordia Univ., pp. 855-866, Suen et al., "Recognition of Totally Unconstrained Handwritten Zip Codes".
Proceedings of the IEEE, vol. 56, No. 8, Aug. 1968, pp. 1292-1301, "Recognition of Handwritten Numerical Characters . . .".
Datamation Reprint, Oct. 1970, Arthur W. Holt, "Smart Terminals".
Computer Design, Feb. 1974, pp. 85-89, "Algorithm for a Low Cost Hand Print Reader".
IBM J. Res. Develop., vol. 27, No. 4, Jul. 1983, "Image Thresholding for Optical Character Recognition . . .", pp. 400-411 (J. M. White et al.).
IBM J. Res. Develop., vol. 27, No. 4, Jul. 1983, "A Processor-Based OCR System", pp. 386-399 (R. G. Casey et al.).
Proceedings of the IEEE, vol. 68, No. 4, Apr. 1980, pp. 469-487, "Automatic Recognition of Handprinted Characters--The State of the Art" (C. U. Suen et al.)
IEEE Transactions on Military Electronics, Apr.-Jul. 1963, pp. 113-115, "A Discrete Model for Eye Tracking".
Scientific America, Jun. 1982, pp. 124-134, "Brain Mechanisms of Visual Attention " (Wartz et al.).
3rd Advanced Technology Conference, pp. 813-826, May 3-5, 1988, Mitchell et al., "Advanced Research in Recognition . . .".
Bell Communications Research, pp. 722-735, Karen Kukich, "Variations on a Back Propagation Name . . .".
State Univ. of New York, pp. 751-767, Pawlicki et al., "Neural Network Models and Their Application to . . .".
Byte, Oct. 1987, pp. 155-162, Jones et al., "Back Propagation--A generalized Delta Learning Rule".
Omni, Erik Larson, "Neural Chips", pp. 113, 114, 116, 168 & 169.
Science News, vol. 132, p. 14, Karen Hartley, "Seeing the Need for `Art`", p. 14.
Univ. of Arkansas, pp. 303-317, Bass, "Connectionist Architectures for Postal Applications".
State Univ. of New York, pp. 318-326, Palumbo et al., "Advanced Computer Architectures for Address Block . . .".
Eastman Kodak Co., pp. 343-359, Cok et al., "A Medium Grained Parallel Computer for Image Processing".
Science News, vol. 132, p. 76, Stefi Weisburd, "Neural Nets Catch the ABCs of DNA", p. 76.
Byte, Oct. 1987, pp. 183-192, Gary Josin, "Neural-Network Heuristics".
IEEE ASSP Magazine, Apr. 1987, pp. 4-22, Lippman, "An Introduction to Computing with Neural Nets".
Discover, Feb. 1988, pp. 70-79, Heppenheimer, "Nerver of Silicon".
"Inventor of Thinking Computer", T. J. Sejnowski, 1-p. 8.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Character and pattern recognition machine and method does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Character and pattern recognition machine and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Character and pattern recognition machine and method will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-46061

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.