Image analysis – Histogram processing – For setting a threshold
Patent
1992-03-30
1994-12-06
Moore, David K.
Image analysis
Histogram processing
For setting a threshold
395 23, 395 24, G06K 962
Patent
active
053718097
ABSTRACT:
Each processing element has a number of weights for each input connection. These weights are coefficients of a polynomial equation. The use of quadratic nodes permits discrimination between body pixel and edge pixels, in which an intermediate value is present, using a grey scale image. In the training method of the present invention, the middle layer is initially one leaf node which is connected to each output node. The contribution of each leaf node to the total output error is determined and the weights of the inputs to the leaf nodes are adjusted to minimize the error. The leaf node that has the best chance of improving the total output error is then "converted" into a branch node with two leaves. A branch node selected from a pool of trial branch nodes is used to replace the chosen leaf node. The trial branch nodes are then trained by gradient training to optimize the branch error function. From the set of trial branch nodes, the best performing node is selected and is substituted for the previously-selected leaf node. Two new leaf nodes are then created from the newly-substituted best-performing-branch node. A leaf node is accepted or rejected based upon the number of times it was activated related to the correctness of the classification. Once a leaf node is rejected, it is eliminated from any further operation, thereby minimizing the size of the network. Integer mathematics can be generated within the network so that a separate floating point coprocessor is not required.
REFERENCES:
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4761746 (1988-08-01), Tano et al.
patent: 4802103 (1989-01-01), Faggin et al.
patent: 4805225 (1989-02-01), Clark
patent: 4807168 (1989-02-01), Moopenn et al.
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5048097 (1991-09-01), Gaborski et al.
patent: 5052043 (1991-09-01), Gaborski
patent: 5054094 (1991-10-01), Barski
patent: 5218646 (1993-07-01), Sirat et al.
patent: 5220618 (1993-06-01), Sirat et al.
Hirose et al., "Back Propagation Algorithm Which Varies the Number of Hidden Units", IEEE Trans. on Neural Networks, vol. 4, No. 1 pp. 61-66 (1991).
Karnin, "A Simple Procedure for Pruning Back-Propagation Trained Neural Networks", IEEE Trans on Neural Nets, vol. 1, No. 2 pp. 240-242 (Jun. 1990).
Quinlan, "Simplifying Decision Trees", Int. J Man-Machine Studies (1987) vol. 27, pp. 221-234.
Sethi et al., "Efficient Decision Tree Design . . . " Pattern Recognition vol. 9, pp. 197-206 (1977).
"Pattern Classification Using Neural Networks", Richard P. Lippmann, IEEE Communications Magazine, Nov. 1989, pp. 47-50, 59-63.
"Quadratic Function Nodes: Use, Structure and Training", Dennis J. Volper et al., Neural Networks, vol. 3, 1990, pp. 93-107.
"Optimal Partitioning for Classification and Regression Trees", Philip A. Chou, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, No. 4, Apr., 1991, pp. 340-354.
"Fast Training Algorithms, for Multilayer Neural Nets", Richard P. Brent, IEEE Transactions on Neural Networks, vol. 2, No. 3, May, 1991, pp. 346-353.
"Entropy Nets: From Decision Trees to Neural Networks", Ishwar K. Sethi, Proceedings of the IEEE, vol. 78, No. 10, Oct., 1990, pp. 1605-1613.
Cammarata Michael
Moore David K.
LandOfFree
Neural network for improved classification of patterns which add does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network for improved classification of patterns which add, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network for improved classification of patterns which add will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-220763