Image analysis – Learning systems – Neural networks
Reexamination Certificate
2001-01-22
2002-07-23
Mehta, Bhavesh (Department: 2621)
Image analysis
Learning systems
Neural networks
C382S232000, C382S240000, C382S281000
Reexamination Certificate
active
06424737
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates generally to image compression. More particularly, the present invention relates image compression using neural networks.
BACKGROUND OF THE INVENTION
Wavelet transforms are widely used in analysis, where they are known as “multiresolution analysis”, and in image and audio compression, where they are used as a pyramid coding method for lossy compression. The wavelets used are generally from a very small set of analytically designed wavelets, such as Daubechies wavelets, or quadrature mirror filters (“QMF”). For some applications, designing specific wavelets with special coding properties would be beneficial.
Presently, compression methods directed to image and video compression attempt to minimize the amount of bandwidth used for a single band. There are no compression methods directed to reducing the amount of total activity in a network.
SUMMARY OF THE INVENTION
A method and apparatus of compressing data is described. The method and apparatus include constructing a neural network having a specific geometry using a finite and discrete Radon transform. The data is then fed through the neural network to produce a transformed data stream. The transformed data stream is thresholded. A fixed input signal is fed back through the neural network to generate a decoding calculation of an average value. The thresholded data stream is entropy encoded.
REFERENCES:
patent: 5414804 (1995-05-01), McWaid
patent: 5686961 (1997-11-01), Gasztonyi et al.
patent: 5953452 (1999-09-01), Boone et al.
patent: 6223195 (2001-04-01), Tonomura
patent: 6259396 (2001-07-01), Pham et al.
International Search Report, PCT/US01/02430, pp. 4.
Rising, “Inversion Processes in the Human Visual System,” vol. 3959 (2000), Sony MediaSoft Lab, U.S. Research Labs, San Jose, California, pp. 400-410.
Albanesi, “Thresholding Wavelets for Image Compression”, 1998, IEEE, University of Pavia, Dipartimento di Informatica e Sistemistica, pp. 374-389.
Ahmed, et al., “Application of Multi-layer Neural Networks to Image Compression”, 1997 IEEE, International Symposium on Circuits and Systems, Jun. 9-12, 1997, Hong Kong, pp. 1273-1276.
Meir, et al., “Stochastic Approximation by Neural Networks Using the Radon and Wavelet Transforms”, 1998 IEEE, Department of Electrical Engineering, Israel, pp. 224-233.
Carroll, et al., “Construction of Neural Nets Using the Radon Transform”, Department of Electrical Engineering, Princeton University, IJCNN International Joint Conference On Neural Networks, Jun. 19-22, 1989, p. 6.
Khuwaja, et al., “Fingerprint Image Compression”, Physics Department, Kuwait University, IEEE, pp. 517-526.
Fanghanel, et al., “Optimizing Wavelet Transform Coding Using a Neural Network”, 1997 IEEE, Universitat der Bundeswehr Hamburg, pp. 1341-1343.
Anderson, J. R. “Arguments Concerning Representations for Mental Imagery”, Psych. Rev. vol. 85, No. 4, Jul. 1978, pp. 249-277.
Arnold, V. I. “Geometrical Methods in the Theory of Ordinary Differential Equations”, Table of Contents, New York, Springer-Verlag, 1983, p. 5.
Barth, E., et al., “Image Encoding, Labeling, and Reconstruction from Differential Geometry”, CVGIP, Jun. 1992, pp. 428-445.
Beutelspacher, A., et al., “Projective Geometry From Foundations to Applications”, New York, Table of Contents, Cambridge University Press, 1998, p. 3.
Blum, L., et al., “Complexity and Real Computation”, Table of Contents, New York, Springer-Verlag, 1997, pp. 12.
Bolker, E. D. “The Finite Radon Transform”, Integral Geometry, R. L. Bryant, et al., AMS Contemporary Mathemetics, vol. 63, 1984, pp. 27-50.
Buekenhout, F., “Handbook of Incidence Geometry”, Table of Contents, New York, North Holland, Elsevier, 1995, p. 24.
Carroll, S. M., et al., “Construction of Neural Nets Using the Radon Transform”, IJCNN, vol. 1, 1989, pp. 607-611.
Diaconis, P., “Projection Pursuit for Discrete Data”, Technical Report No. 198, Department of Statistics, Stanford University, Apr. 1983, pp. 1-28.
Edelman, S., “Representation, Similarity and the Chorus of Prototypes”, Minds and Machines, Feb. 1995, pp. 45-68.
Helgason, S., “Groups and Geometric Analysis”, Table of Contents, New York, Academic Press, 1984, p. 8.
Ito, Y., “Representations of Functions by Superpositions of a Step or Sigmoid Function and Their Applications to Neural Network Theory”, Neural Networks, vol. 4, No. 3, 1991, pp. 385-394.
Kawakami, S., et al., “A Cell Model for the Detection of Local Image Motion on the Magnocellular Pathway of the Visual Cortex”, Vision Research, vol. 36, No. 1, 117-147, 1996.
Kung, J. P. S., “Reconstructing Finite Radon Transforms”, Nuclear Physics B (Proc. Supl.), vol. 5A, Sep. 1988, pp. 44-49.
Kosslyn, S. M., “Image and Brain” Cambridge, Massachusetts, MIT Press, 1994, p. 34.
Kurusa, A., “The Radon transform on half sphere” Acta Sci. Math. (Szeged), vol. 53, Nos. 1-4, 1993, pp. 143-158.*
Matus, F., et al., “Image Representations via a Finite Radon Transform” IEEE Trans. PAMI, vol. 15, No. 10, Oct. 1993, pp. 996-1006.*
Meyer, Y., “Wavelets Algorithms and Applications”, Philadelphia, SIAM Press, 1993, Table of Contents, p. 10.*
Okamoto, H., “MT neurons in the macaque exhibited two types of bimodal direction tuning as predicted by a model for visual motion detection” Vision Research 39, 1999, pp. 3465-3479.*
Poggio, T., et al., “On the Representation of Multi-Input Systems: Computational Properties of Polynomial Algorithms” Biological Cybernetics, vol. 37, No. 3, Jul. 1980, pp. 167-186.*
Ramm, A. G., et al., “The Radon Transform and Local Tomography”, Table of Contents, New York, CRC Press, 1996, p. 10.
Rising, H. K., “Creating a Biologically Plausible Model of Recognition which Generalizes Multidimensional Scaling” SPIE, vol. 3644, Human Vision and Electronic Imaging IV, Rogowitz, B. E., et al., Jan. 1999, pp. 411-420.
Rising, H. K., “Deriving and combining biologically plausible Processes with the Windowed Radon Transform” SPIE Prnc. vol. 3299, Human Vision and Imaging III, Rogowitz, B. E., et al. Jan. 1998. pp. 519-525.
Rising, H. K., “Assessing the Similarity of Mechanisms in Motion and Color Processing for Synchronization of Visual Pathways”, SPIE, vol. 3016, Human Vision and Imaging II, Rogowitz, B. E., et al., Feb. 1997, pp. 302-312.
Rolls, E. T., et al. “Neural Networks and Brain Function”, New York: Oxford University Press, Preface and Table of Contents, 1998, p. 5.
Shepard, D., “Optimizing the Delivery of Radiation Therapy to Cancer Patients”, SIAM Review, vol. 41, No. 4, 1999, pp. 721-744.
Siegelmann, H. T., et al., “On the Computational Power of Neural Nets”, Proceedings of the 5th ACM Workshop on Computational Learning Theory, Jul. 1992, pp. 440-49.
Vvedenskaya, N. D., et al., “Discrete Radon Transform and Image Reconstruction” Mathematical Problems in Tomography., Gelfand, I. M., et al., AMS, vol. 81, 1990, pp. 141-188.
Wallis, W. D., “Combinatorial Designs”, Table of Contents, New York, Marcel Dekker, 1988, p. 10.
Zeki, S., “A Vision of the Brain”, Table of Contents, Boston, Blackwell Scientific Publications, 1994, p. 5.
Blakely , Sokoloff, Taylor & Zafman LLP
Mehta Bhavesh
LandOfFree
Method and apparatus of compressing images using localized... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus of compressing images using localized..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus of compressing images using localized... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2865744