Object recognition system employing a sparse comparison neural n

Details Object recognition system employing a sparse comparison neural n Object recognition system employing a sparse comparison neural n

1991-06-28

1994-03-08

Fleming, Michael R.

Image analysis

Histogram processing

For setting a threshold

395 21, 395 22, 382 14, G06K 966

Patent

active

052934560

ABSTRACT:
A neural network for comparing a known input to an unknown input comprises a first layer for receiving a first known input tensor and a first unknown input tensor. A second layer receives the first known and unknown input tensors. The second layer has at least one first trainable weight tensor associated with the first known input tensor and at least one second trainable weight tensor associated with the first unknown input tensor. The second layer includes at least one first processing element for transforming the first known input tensor on the first trainable weight tensor to produce a first known output and at least one second processing element for transforming the first unknown input tensor on the second trainable weight tensor to produce a first unknown output. The first known output comprises a first known output tensor of at least rank zero and has a third trainable weight tensor associated therewith. The first unknown output comprises a first unknown output tensor of at least rank zero and has a fourth trainable weight tensor associated therewith. The first known output tensor and the first unknown tensor are combined to form a second input tensor. A third layer receives the second input tensor. The third layer has at least one fifth trainable weight tensor associated with the second input tensor. The third layer includes at least one third processing element for transforming the second input tensor on the fifth trainable weight tensor, thereby comparing the first known output with the first unknown output and producing a resultant output. The resultant output is indicative of the degree of similarity between the first known input tensor and the first unknown input tensor.

REFERENCES:
patent: 4803736 (1989-02-01), Grossberg et al.
patent: 4805225 (1989-02-01), Clark
patent: 4876731 (1989-10-01), Loris et al.
patent: 4953099 (1990-08-01), Jourjine
patent: 4979126 (1990-12-01), Pao et al.
patent: 4995090 (1991-02-01), Singh et al.
patent: 5058179 (1991-10-01), Denker et al.
patent: 5059814 (1991-10-01), Mead et al.
patent: 5067164 (1991-11-01), Denker et al.
patent: 5109431 (1992-03-01), Nishiya et al.
patent: 5150425 (1992-09-01), Martin et al.
patent: 5181256 (1993-01-01), Kamiya
Lippmann, R. P., "An Introduction to computing with Neural Nets," IEEE ASSP Mag., Apr. 1987, 4-22.
Cortes et al., "A Network System for Image Segmentation", IJCNN 1989, I-121-I-125.
Lippmann, R. P., "Pattern Classification Using Neural Networks", IEEE Communications Mag., Nov. 1989, 47-64.
Le Cun et al., "Handwritten Digit Recognition:Applications Neural Network Chips and Automatic Learning", IEEE Comm-Mag., Nov. 1989, 41-46.
Iwata et al., "A Large Scale Neural Network `CombNET` and its Application to Chinese Character Recognition", Intl. Neural Network Conf., Jul. 1990, 83-86.
Jacobs et al., "Adaptive Mixtures of Local Experts", Neural Computation May 3, 1991, 79-87.
Kohonen, T., "Correlation Matrix Memories," IEEE Transactions on Computers, Apr. 1972, 353-359.
Sholl, H. A., "Modeling of an Operator's Performance in a Short-Term Visual Information Processing Task," IEEE Trans. on Sys., Man. and Cybernetics, Jul. 1972, 352-362.
Fukushima, K. "Self-organizing Neural Network Models for Visual Pattern Recognition", Acta Neurochirurgica. Suppl. 41, 51-67 (1987).
Fukushima, K. "A Neural Network Model for Selective Attention in Visual Pattern Recognition", Biol. Cybern. 55, 5-15 (1986).
Parallel Distributed Processing, Volume 1: Foundations, Rumelhart, McClelland and the PDP Research Group, editors, MIT Press, Cambridge, Mass. (1986, Sixth printing 1987), Chapter 8, pp. 318-362.
IEEE International Conf. on Neural Networks, vol. 2, 24 Jul. 1988, San Diego, USA, pp. 525-532, SAMAD, `Towards Connectionist Rule-Based Systems`.

Affiliated with

Also associated with

Rating

Object recognition system employing a sparse comparison neural n does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Object recognition system employing a sparse comparison neural n, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object recognition system employing a sparse comparison neural n will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-159435