Image analysis – Learning systems – Trainable classifiers or pattern recognizers
Patent
1997-09-04
2000-09-19
Mancuso, Joseph
Image analysis
Learning systems
Trainable classifiers or pattern recognizers
706 20, 382158, G06K 962
Patent
active
061223999
ABSTRACT:
The present invention provides a novel pattern recognition system that may be used to determine the likelihood that an unknown item belongs to a predefined class. The present invention provides improved functionality over prior art systems in that both feature parameters and confidence parameters are trained automatically from ground truth image data; large numbers of different attributes can be analyzed in the model, which yields more accurate modeling; relationships between different features can also be trained from ground truth data and represented in parametric form; there is insensitivity to feature noise; parameters are based exclusively on statistical information; the need for heuristic information is minimized; retraining is straightforward and fast; on-line updating of model parameters is possible; and the models created are accurate and reliable at predicting the match of an unknown item to the model.
REFERENCES:
patent: 5371809 (1994-12-01), Desieno
patent: 5638491 (1997-06-01), Moed
patent: 5812700 (1998-09-01), Fang et al.
Multiple sensor target classification using an unsupervised hybrid neural network, by Gelli et al. 0-7803-1901-X/94 IEEE, pp. 4028-4032, 1994.
Robotic Task Planning Using A Connectionist/Symbolic System, Moed et al., p. 296-316.
Bali Vikkram
Mancuso Joseph
NCR Corporation
LandOfFree
Pattern recognition constraint network does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Pattern recognition constraint network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern recognition constraint network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1081530