Image analysis – Learning systems – Neural networks
Patent
1994-08-25
1998-07-21
Boudreau, Leo
Image analysis
Learning systems
Neural networks
382161, 382220, G06K 962
Patent
active
057844852
ABSTRACT:
The present invention relates to a new and useful Automated Pattern Recognition Device comprising a neural-network system, implemented on a general purpose computer, and capable of recognizing not only printed characters but also handwritten characters and other patterns in n-dimensions. The system incorporates novel feature extraction which generates an additional dimension from an n-dimensional input pattern, for example, a three-dimensional feature pattern from a two dimensional input pattern, resulting in shift-invariance, scale-invariance, and invariance to slight rotation.
REFERENCES:
patent: 4153897 (1979-05-01), Yasuda et al.
patent: 4805225 (1989-02-01), Clark
patent: 4817171 (1989-03-01), Stentiford
patent: 5058184 (1991-10-01), Fukushima
patent: 5065440 (1991-11-01), Yoshida et al.
patent: 5422981 (1995-06-01), Niki
Fukushima, et al.; "Neocognition: A Neural Network Model for a Mechanism os Visual Pattern Recognition", 13 IEEE Transactions on Man, Systems and Cybernetics 826-834 (Sep./Oct. 1983).
Memon & Heinemann (`Classification of Patterns using a self-organizing neural network`), Neural Networks, vol. 1, 1988, pp. 201-215.
Barnard & Casasent (`Shift invariance and the Neocognitron`), Neural Networks, vol. 3, 1990, pp. 403-410.
Chang Chein-I
Xu Youguang
Boudreau Leo
Tran Phuoc
LandOfFree
Method and apparatus for automated pattern recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for automated pattern recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for automated pattern recognition will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1655190