Pattern recognition with hierarchical networks

Details Pattern recognition with hierarchical networks Pattern recognition with hierarchical networks

2007-12-11

2007-12-11

Mehta, Bhavesh M (Department: 2624)

Image analysis

Learning systems

Trainable classifiers or pattern recognizers

C382S160000, C382S228000, C700S047000

Reexamination Certificate

active

10155948

ABSTRACT:
Within the frameworks of hierarchical neural feed-forward architectures for performing real-world 3D invariant object recognition a technique is proposed that shares components like weight-sharing (2), and pooling stages (3, 5) with earlier approaches, but focuses on new methods for determining optimal feature-detecting units in intermediate stages (4) of the hierarchical network. A new approach for training the hierarchical network is proposed which uses statistical means for (incrementally) learning new feature detection stages and significantly reduces the training effort for complex pattern recognition tasks, compared to the prior art. The incremental learning is based on detecting increasingly statistically independent features in higher stages of the processing hierarchy. Since this learning is unsupervised, no teacher signal is necessary and the recognition architecture can be pre-structured for a certain recognition scenario. Only a final classification step must be trained with supervised learning, which reduces significantly the effort for adaptation to a recognition task.

REFERENCES:
patent: 5058179 (1991-10-01), Denker et al.
patent: 5067164 (1991-11-01), Denker et al.
patent: 5293456 (1994-03-01), Guez et al.
patent: 5422981 (1995-06-01), Niki
patent: 5497430 (1996-03-01), Sadovnik et al.
patent: 5500905 (1996-03-01), Martin et al.
patent: 5774586 (1998-06-01), LeCun
patent: 5822742 (1998-10-01), Alkon et al.
patent: 5995644 (1999-11-01), Lai et al.
patent: 6038337 (2000-03-01), Lawrence et al.
patent: 6105015 (2000-08-01), Nguyen et al.
patent: 6278799 (2001-08-01), Hoffman
patent: 6728642 (2004-04-01), Bloch et al.
patent: 2003/0059106 (2003-03-01), Gutta
Lecun Y., Bottou L., Bengio Y. and Haffner P., “Gradient Based Learning Applied to Document Recognition” The Proceedings of IEEE, vol. 86 No. 11, Nov. 1998, pp. 2278-2324.
Lee T., Lewicki M. and Sejnowski T., “ICA Mixture Models for Unsupervised Classification of Non-Gaussin Classes and Automatic Context Switchong in Blind Signal Separation” IEEE PAMI, vol. 22 No. 10, Oct. 2000, pp. 1078-1089.
Wallis G., “Using Spatio-temporal Correlations to Learn Invariant Objects Recognition” Neural Networks, vol. 9 No. 9, 1996, pp. 1513-1519.
Becker et al., “Unsupervised Neural Network Learning Procedures for Feature Extraction and Classification”, Applied Intellegence 6, 185-203, 1996.
Jain et al., “Statistical Pattern Recognition: A Review”, IEEE Trans. on Pattern Recognition and Machine Intelligence, vol. 22, No. 1, Jan. 2000, 4-37.
“Viewpoint invariant face recognition using independent component analysis and attractor networks” by Bartlett et al. Bartlett, M. and Sejnowski, T. J. 1997. Viewpoint invariant face recognition using independent component analysis and attractor networks. In Advances in Neural Information Processing Systems 9, 817-823.
Bartlett M.S. et al.; “Learning Viewpoint-Invariant Face Representations From Visual Experience In An Attractor Network”; Network: Computer Neural Systems, IOP Publishing, Bristol, GB, vol. 9, No. 3, Aug. 1, 1998, pp. 399-417, XP000783461.
Romero R.D. et al.; “Optical Chinese Character Recognition Using Probabilistic Neural Networks”, Pattern Recognition, Pergamon Press Inc., Elmsford, N.Y., US, vol. 30, No. 8, Aug. 1, 1997, pp. 1279-1292, XP004074588.
Dailey M.N. et al.; “Organization Of Face And Object Recognition In Modular Neural Network Models”; Neural Networks, Elsevier Science Publishers, Barking, GB, vol. 12, No. 7-8, Oct. 1999, pp. 1053-1074, XP004180497.
Lee T-W. et al.; “ICA Mixture Models For Unsupervised Classification Of Non-Gaussian Classes And Automatic Context Switching In Blind Signal Separation”; IEEE Transactions on Pattern Analysis And Machine Intelligence, IEEE Inc. New York, US, vol. 22, No. 10, Oct. 2000, pp. 1078-1089, XP000976544.
Abramowicz H. et al.; “An Orientation Selective Neural Network And Its Application To Cosmic Muon Identification”; Nuclear Instruments & Methods In Physics Research, Section—A: Accelerators, Spectrometers, Detectors And Associated Equipment, North-Holland Publishing Company; Amsterdam, NL, vol. 378, No. 1, Aug. 11, 1996, pp. 305-311, XP004011429.
Wallis G.; “Using Spatio-Temporal Correlations To Learn Invariant Object Recognition”; Neural Networks, Elsevier Science Publishers, Barking, GB, vol. 9, No. 9, Dec. 1, 1996, pp. 1513-1519, XP004096094.
European Search Report, EP 01113014, Apr. 15, 2002, 5 pages.

Affiliated with

Also associated with

Rating

Pattern recognition with hierarchical networks 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 with hierarchical networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern recognition with hierarchical networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3889634