System for self-organization of stable category recognition code

Details System for self-organization of stable category recognition code System for self-organization of stable category recognition code

1987-06-19

1990-04-03

Blum, Theodore M.

Image analysis

Histogram processing

For setting a threshold

G06K 962

Patent

active

049147080

ABSTRACT:
A neural network includes a feature representation field which receives input patterns. Signals from the feature representation field select a category from a category representation field through a first adaptive filter. Based on the selected category, a template pattern is applied to the feature representation field, and a match between the template and the input is determined. If the angle between the template vector and a vector within the representation field is too great, the selected category is reset. Otherwise the category selection and template pattern are adapted to the input pattern as well as the previously stored template. A complex representation field includes signals normalized relative to signals across the field and feedback for pattern contrast enhancement.

REFERENCES:
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4044243 (1977-08-01), Cooper et al.
patent: 4227177 (1980-10-01), Moshier
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4319331 (1982-03-01), Elbaum et al.
patent: 4326259 (1982-04-01), Cooper et al.
WO, A, 87/02805 (Nippon Hoso Kyokai) 7 May 1987, see abstract.
EP, A, 0245508 (Nippon Hoso Kyokai) 19 Nov. 1987.
K. Kukushima: "A hierarchical neural network model for associative memory," Electronics & Communications in Japan, vol. 66, No. 12, Dec. 1983, Scripta Publishing Co., (Silver Spring, Maryland, US), pp. 43-52, see page 44, paragraph 2(a).
G. A. Carpenter et al.: "Art 2: self-organization of stable category, IEEE First International Conference on Neural Networks", Sheraton Harbor Island East San Diego, California, 21st-24th Jun. 1987, pp. II-727-II-735.
Carpenter, G. A. and Grossberg, S., A massively parallel architecture for a self-organizing neural pattern recognition machine, Computer Vision, Graphics, and Image Processing, Feb., 1986.
Carpenter, G. A. and Grossberg, S., Absolutely stable learning of recognition codes by a self-organizing neural network, AIP, Snowbird meeting, May 1986.
Carpenter, G. A. and Grossberg, S., Neural dynamics of category learning and recognition: structural invariants, reinforcement, and evoked potentials, Pattern Recognition and Concepts in Animals, People, and Machines, Aug. 1985.
Carpenter, G. A. and Grossberg, S., Category learning and adaptive pattern recognition: A neural network model, Proceedings of the Third Army Conference on Applied Mathematics and Computing, 1985.
Patent Application PCT/US 86/02553, Gail A. Carpenter and Stephen Grossberg.

Affiliated with

Also associated with

Rating

System for self-organization of stable category recognition code does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System for self-organization of stable category recognition code, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for self-organization of stable category recognition code will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1363619