Eliminating invariances by preprocessing for kernel-based method

Details Eliminating invariances by preprocessing for kernel-based method Eliminating invariances by preprocessing for kernel-based method

1997-03-27

2000-08-29

Hafiz, Tariq R.

Data processing: artificial intelligence

Neural network

Learning task

G06F 1035, G06F 500

Patent

active

061121959

ABSTRACT:
A kernel-based method and apparatus includes a preprocessor, which operates on an input data in such a way as to provide invariance under some symmetry transformation.

REFERENCES:
patent: 4838644 (1989-06-01), Ochoa et al.
patent: 5054094 (1991-10-01), Barski
patent: 5263107 (1993-11-01), Ueda et al.
patent: 5729662 (1998-03-01), Rozmus
patent: 5926568 (1999-07-01), Cheney et al.
patent: 5950146 (1999-09-01), Vapnik
patent: 5956427 (1999-09-01), Greenspan et al.
patent: 5969524 (1999-10-01), Pierpaoli et al.
Gilbert Strang, Linear Algebra and Its Applications, Third edition 341-42, 1988.
Microsoft Press, Computer Dictionary, Third Edition, 272, 375, 1997.
R.P. Lippmann, "Pattern Classification Using Neural Networks," IEEE Communications Magazine, vol. 27 (11), pp. 47-64, Nov. 1989.
A. Khotanzad and J.-H. Lu, "Classification of Invariant Image Representations Using a Neural Network," IEEE Trans. on Accoustics, Speech, and Signal Processing, vol. 38 (6), pp. 1028-1038, Jun. 1990.
J.I. Minnix, et al., Multistaged Self-Organizing Neural Network with Biologically Inspired Preprocessing Features for Rotation and Scale Invariant Pattern Recognition, vol. 3, pp. 1605-1610, Oct. 1991.
S.J. Perantonis and P.J.G. Lisboa, "Translation, Rotation, and Scale Invariant Pattern Recognition by High-Order Neural Networks and Moment Classifiers," IEEE Trans. on Neural Networks, vol. 3(2), pp. 241-251, Mar. 1992.
C. Yuceer and K. Oflazer, "A Rotation, Scaling and Translation Invariant Pattern Classification System," Proc. 11th IAPR Int'l Conf. on Pattern Recognition, vol. II, pp. 422-425, Sep. 1992.
J.A. Starzyk and S. Chai, "Vector Contour Representation for Object Recognition in Neural Networks," 1992 IEEE Int'l Conf. on Systems, Man and Cybernetics, vol. 1, pp. 399-404, Oct. 1992.
Y. Onodera, et al., "Translation and Rotation-Invariant Pattern Recognition Method Using Neural Network with Back-Propagation," Communications on the Move, ICCS/ISITA '92, vol. 2, pp. 548-552, Nov. 1992.
P.Y. Simard, et al., "Memory-Based Character Recognition Using a Transformation Invariant Metric," Proc. 12th Int'l Conf. on Pattern Recognition, pp. 262-267, Oct. 1994.
Q.-S. Chen, et al., "Symmetric Phase-Only Matched Filtering of Fourier-Mellin Transforms for Image Registration and Recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 16(12), pp. 1156-1168, Dec. 1994.
J. Tanomaru and A. Inubushi, "A Compact Representation of Binary Patterns for Invarinat Recognition," 1995 IEEE Int'l Conf. on Systems, Man and Cybernetics, vol. 2, pp. 1550-1555, Oct. 1995.
E.A. Heredia and G.R. Arce, "Piecewise Polynomial Kernel Networks," Proc. Int'l. Conf. on Neural Networks, pp. 1558-1563, Jun. 1996.
C. J. C. Burges et al., "Improving the Accuracy and speed of support vector machines", Advances in Neural Information Processing Systems 9. Proceedings of the 1996 Conference, Advances in Neural Information Processing Systems 9, Proceedings of the 1996 Conference, Denver, CO, USA, Dec. 2-5, 1996, pp. 375-381, XP002088166, ISBN 0-262-10065-7, 1997, London, UK, MIT Press, UK, *the whole document* particularly relevant if taken alone.
P. Y. Simard et al., "Memory-Based Character Recognition Using a Transformation Invariant Metric", Proceedings of the IAPR International Conference on Pattern Recognition, Jerusalem, Oct. 9-13, 1994 Conference B: Pattern Recognition and Neural Networks, vol. 2, No. Conf. 12, Oct. 9, 1994, pp. 262-267, XP000509894, Institute of Electrical and Electronics Engineers, *Abstract* technological background.
Hidefumi Sawai, "Axially Symmetric Neural Network Architecture for Rotation-Invariant Patter Recognition", International Conference on Neural Networks/World Congress on Computational Intelliges, Orlando, Jun. 27-19, 1994, vol.7, Jun. 27, 1994, pp. 4253-4258, XP000531357, Institute of Electrical and Electronics Engineers, *Abstract*.
Mas J. et al: Invariant Perception for Symmetry Related Patterns, International Joint Conference on Neural Networks (IJCNN), Washington, Jun. 19-22, 1989., vol. 1, Jun. 19, 1989, pp. 85-89, XP000088251, Institute of Electrical and Electronic Engineers--*Abstract*.
"Extracting Support Data For A Given Task," B. Scholkopf, et al., Eds. Proceedings, International Conference on Knowledge Discovery & Data Mining, AAAI Press, Menlo Park, CA 1995.
"Incorporating Invariances in Support Vector Learning Machines", B. Schoklopf et al., Proceedings ICANN'96--International Conference on Artificial Neural Networks, Springer Verlag, Berlin 1996.

Affiliated with

Also associated with

Rating

Eliminating invariances by preprocessing for kernel-based method does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Eliminating invariances by preprocessing for kernel-based method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Eliminating invariances by preprocessing for kernel-based method will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1258973