Hierarchical constrained automatic learning neural network for c

Details Hierarchical constrained automatic learning neural network for c Hierarchical constrained automatic learning neural network for c

1989-11-30

1991-11-19

Moore, David K.

Image analysis

Histogram processing

For setting a threshold

3642766, G06K 962

Patent

active

050671642

ABSTRACT:
Highly accurate, reliable optical character recognition is afforded by a layered network having several layers of constrained feature detection wherein each layer of constrained feature detection includes a plurality of constrained feature maps and a corresponding plurality of feature reduction maps. Each feature reduction map is connected to only one constrained feature map in the same layer for undersampling that constrained feature map. Units in each constrained feature map of the first constrained feature detection layer respond as a function of a corresponding kernel and of different portions of the pixel image of the character captured in a receptive field associated with the unit. Units in each feature map of the second constrained feature detection layer respond as a function of a corresponding kernel and of different portions of an individual feature reduction map or a combination of several feature reduction maps in the first constrained feature detection layer as captured in a receptive field of the unit. The feature reduction maps of the second constrained feature detection layer are fully connected to each unit in the final character classification layer. Kernels are automatically learned by constrained back propagation during network initialization or training.

REFERENCES:
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4774677 (1988-09-01), Buckley
patent: 4897811 (1990-01-01), Scofield
D. E. Rumelhart et al., Parallel Distr. Proc.: Explorations in Microstructure of Cognition, vol. 1, 1986, "Learning Internal Representations by Error Propagation", pp. 318-362.
R. P. Lippmann, IEEE ASSP Magazine, vol. 4, No. 2, Apr. 1987, "An Introduction to Computing with Neural Nets", pp. 4-22.
Y. LeCun, Connectionism in Perspective, R. Pfeifer, Z. Schreter, F. Fogelman, L. Steels, (Eds.), 1989, "Generalization and Network Design Strategies", pp. 143-55.
Y. LeCun et al., IEEE Comm. Magazine, Nov. 1989, "Handwritten Digit Recognition: Applications of Neural . . . ", pp. 41-46.

Affiliated with

Also associated with

Rating

Hierarchical constrained automatic learning neural network for c does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Hierarchical constrained automatic learning neural network for c, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hierarchical constrained automatic learning neural network for c will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1375767