Self-organizing pattern classification neural network system

Details Self-organizing pattern classification neural network system Self-organizing pattern classification neural network system

1992-02-06

1993-08-24

Mancuso, Joseph

Image analysis

Histogram processing

For setting a threshold

382 36, 395 24, G06K 962

Patent

active

052395944

ABSTRACT:
A self-organizing pattern classification neural network system includes means for receiving incoming pattern of signals that were processed by feature extractors that extract feature vectors from the incoming signal. These feature vectors correspond to information regarding certain features of the incoming signal. The extracted feature vectors then each pass to separate self-organizing neural network classifiers. The classifiers compare the feature vectors to templates corresponding to respective classes and output the results of their comparisons. The output from the classifier for each class enter a discriminator. The discriminator generates a classification response indicating the best class for the input signal. The classification response includes information indicative of whether the classification is possible and also includes the identified best class. Lastly, the system includes a learning trigger for transferring a correct glass signal to the self-organizing classifiers so that they can determine the validity of their classification results.

REFERENCES:
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4044243 (1977-08-01), Cooper et al.
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4774677 (1988-09-01), Buckley
patent: 4805225 (1989-02-01), Clark
patent: 4914708 (1990-04-01), Carpenter et al.
patent: 4958375 (1990-09-01), Reilly et al.
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5048100 (1991-09-01), Kuperstein
patent: 5060278 (1991-10-01), Fukumizu
Sebestyen, G., Decision Making Processes Recognition MacMillan 1962, pp. 17-24, 37-53, 91-96, 108-112, 120-131, 142-151.
R. Duda et al., Pattern Classification and Scene Analysis, 1973, pp. 1-7.
C. Suen et al. "Automatic Recognition of Handprinted Characters-The State of the Art", Proc. of IEEE, Apr. 1980, 469-487.
J. Makhoul et al., "Vector Quantization in Speech Coding", Proc. of IEEE, Nov. 11, 1955, pp. 1551-1588.
R. Lippmann, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
D. Reilly et al., "Learning System Architechtures Composed of Multiple Learning Modules," Proc. of 1st Nat'l Conf. on Neural Info. Proc., 1987.

Affiliated with

Also associated with

Rating

Self-organizing pattern classification neural network system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Self-organizing pattern classification neural network system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Self-organizing pattern classification neural network system will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-835184