Image analysis – Learning systems – Neural networks
Patent
1995-02-27
1997-11-18
Couso, Yon J.
Image analysis
Learning systems
Neural networks
G06K 962
Patent
active
056895810
ABSTRACT:
An inspection method for judging whether an object is defective or not uses a neural network comprising an input neuron which quantizes input feature quantities based on present quantization ranges, a plurality of intermediate neuron coupled to the input neuron with coupling coefficients determined from quantized feature quantities and a pair of output neurons coupled to respective intermediate neurons with intermediate coupling coefficients obtained by learning in which the intermediate coupling coefficients are initially set so that any object is judged to be defective and are fitted so that if an object is nondefective then it is judged to be nondefective by performing learning with use of nondefective objects.
REFERENCES:
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4893346 (1990-01-01), Bishop
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5465308 (1995-11-01), Hutcheson et al.
patent: 5481621 (1996-01-01), Furatomi et al.
Maruno et al., Perception of Letters by Adaptive Propagation and Quantization Neurons, Tech. Rep., Inst Electron. Comm. Eng. Japan, NC 91-51, pp. 23-28, 1991.
Maruno Susumu
Nakao Masaya
Shimeki Yasuharu
Couso Yon J.
Matsushita Electric - Industrial Co., Ltd.
LandOfFree
Methods of inspection does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Methods of inspection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods of inspection will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1571928