Image analysis – Learning systems – Neural networks
Patent
1997-03-13
1999-11-02
Kelley, Christopher S.
Image analysis
Learning systems
Neural networks
382261, G06K 962
Patent
active
059785055
ABSTRACT:
A regularization system and method for image restoration in homogeneous or inhomogeneous environments. The system and method includes features similar to a neural network with intermediate levels of structure including a pixel having processing capabilities; clusters consisting of a plurality of interconnected pixels and also having processing capabilities; and an image space comprised of a plurality of interconnected pixels and clusters and also having processing capabilities. The system and method also include means for assigning a regularization parameter to each pixel depending on the local variance of intensity of pixels; decomposing the image space into clusters of pixels, each cluster having the same regularization parameter; imposing a blurring function on each pixel; rapidly forming a regularized image by simultaneous local and global encoding of a regularization matrix onto each pixel directed through a process of gradient energy decent; and a means of assessing the output image.
REFERENCES:
patent: 5014327 (1991-05-01), Potter et al.
patent: 5274714 (1993-12-01), Hutcheson et al.
patent: 5526446 (1996-06-01), Adelson et al.
patent: 5733721 (1998-03-01), Hemstreet et al.
"Inhomogeneous Cellular Neural Networks: Possibility of Functional Device Design," Y. Andrevev et al., Institute of Radio Engineering and Electronics of Academy of Sciences, Jan. 1992 IEEE, pp. 135-140.
"An Active Vision System for a Location Task Using an Inhomogeneously Blurred Image," T. Yagi et al., Nagoya University and Chubu University, 1994 IEEE, pp. 4333-4336 No Month.
"Recognition and categorization in a structured neural network with attractor dynamics," C. Fassnacht et al., Institut fur Theoretische Physik der Universitat Gottingen, Network 2 (1991), pp. 63-84 No Month.
"A Partitioned Modified Hopfield Neural Network Algorithm for Real-Time Image Restoration," S.W. Perry et al., University of Sydney, J. of Real-Time Imaging, In Press May 1994.
"A Network of Networks Processing Model for Image Regularization," L. Guan et al., IEEE Transactions on Neural Networks, vol. 8 No. 1, Jan. 1997, pp. 1-7.
"Biologically Motivated Neural Computing in Early Vision Processing," L. Guan et al., Proc. IEEE SMC Conf. China, Nov. 1996, pp. 1-6.
"Image restoration by a neural network with hierarchical cluster architecture," L. Guan, University of Sydney, Journal of Electronic Imaging, vol. 3(2), Apr. 1994, pp. 154-163.
"Real-Time Image Filtering: From Optimal Neuron Evolution to Vector Quadratic Programming," L. Guan et al., University of Sydney, Apr. 1994 IEEE, pp. 694-699.
"Mean Field Theory of Nested Neural Clusters," J.P. Sutton, Proceedings Intern, AMSE Conference, Neural Networks, San Diego (USA), May 29-31, 1991, vol. 1, pp. 47-58.
"Hierachical Model of Memory and Memory Loss," Neural Computation in Wake and Sleep, App. B, J. P. Sutton et al., University of Toronto, J. Phys. A: Math. Gen. 21 Apr. (1988) pp. 4443-4454.
"Neural Models 1 : A Hierarchical Model of Neocortical Synaptic Organization," J.P. Sutton et al., University of Toronto, Mathl Comput Modeling, vol. 11, pp. 346-350, 1988, Printed in GB No Month.
Guan Ling
Sutton Jeffrey P.
Kelley Christopher S.
Massachusetts General Hospital
The University of Sydney
LandOfFree
System and method for image regularization in inhomogeneous envi does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for image regularization in inhomogeneous envi, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for image regularization in inhomogeneous envi will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2146572