Image analysis – Histogram processing – For setting a threshold
Patent
1991-01-31
1993-11-16
Boudreau, Leo H.
Image analysis
Histogram processing
For setting a threshold
382 15, 395 22, G06K 962
Patent
active
052631079
ABSTRACT:
A neural network system and method of operating same wherein input data are initialized, then mapped onto a predetermined array for learning or recognition. The mapped information is divided into sub-input data or receptive fields, which are used for comparison of the input information with prelearned information having similar features, thereby allowing for correct classification of the input information. The receptive fields are shifted before the classification process, in order to generate a closest match between features which may be shifted at the time of input, and weights of the input information are updated based upon the closest-matching shifted position of the input information.
REFERENCES:
patent: 4136332 (1979-01-01), Kadota et al.
patent: 4760604 (1988-07-01), Cooper et al.
patent: 5048100 (1991-09-01), Kuperstein
patent: 5060276 (1991-10-01), Morris et al.
patent: 5067164 (1991-11-01), Denker et al.
Kohonen et al., IEEE, Proc. of ICNN vol. 1, pp. 1-61 to 1-68.
Rumelhart et al., Eds., Parrallel Distributed Processing: Explorations in the Microstructure of Cognition (1986) vol. 1, Chapter 8, pp. 318-362.
Waibel et al., IEEE Trans. Acoustics, Speech, Signal Processing (1989) vol. 37, No. 12, pp. 1888-1898.
Le Cun et al., Neural Information Processing Systems 2 Touretzky, D., ed., Morgan Kaufmann Publishers, (1989) vol. 2, pp. 396-404.
IBM Technical Disclosure Bulletin, vol. 27, No. 6, Nov., 1984 pp. 3423-3424.
Togawa Fumio
Ueda Toru
Boudreau Leo H.
Kelley Christopher
Sharp Kabushiki Kaisha
LandOfFree
Receptive field neural network with shift-invariant pattern reco does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Receptive field neural network with shift-invariant pattern reco, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Receptive field neural network with shift-invariant pattern reco will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-27575