John E. Tansley, Martin J. Oldfield, David J.C. MacKay  Home/Search
Context Related
| toronto.edu/~mackay...nn_im_decon.ps.gz wol.ra.phy.cam.ac.u...nn_im_decon.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: wol.ra.phy.cam.ac.uk/pub...README (more) From: wol.ra.phy.cam.ac.uk/pub...README (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: . We examine the problem of deconvolving blurred text. This is a task in which there is strong prior knowledge (e.g., font characteristics) that is hard to express computationally. These priors are implicit, however, in mock data for which the true image is known. When trained on such mock data, a neural network is able to learn a solution to the image deconvolution problem which takes advantage of this implicit prior knowledge. Prior knowledge of image positivity can be hard--wired into the... (Update)
Context of citations to this paper: More
.... lter assumes that the source image consists of independent identically distributed Gaussian pixels and so does not force positivity [4] [8]. 2 James Miskin, David J. C. MacKay Another problem is that we know that the convolution lters must also be positive (in the case of...
Cited by: More
Ensemble Learning for Blind Image Separation and Deconvolution - Miskin, MacKay (2000) (Correct)
Similar documents (at the sentence level):
11.1%: Information Theory, Inference, and Learning Algorithms - MacKay (2003) (Correct)
Active bibliography (related documents): More All
0.0: Parametric Deconvolution of Positive Spike Trains - Lei Li Florida (2000) (Correct)
0.0: Maximum Entropy Modeling with Clausal Constraints - Dehaspe (1997) (Correct)
0.0: Penalized Likelihood - Green (1996) (Correct)
Similar documents based on text: More All
0.4: Generalization Error and the Number of Hidden Units in a.. - MacKay, Oldfield (1995) (Correct)
0.2: Sparse-Graph Codes for Quantum Error-Correction - David Mackay Cavendish (2003) (Correct)
0.2: Latent Variable Models for Gene Expression Data - MacKay, Miskin (2001) (Correct)
BibTeX entry: (Update)
John E. Tansley, Martin J. Oldeld, and David J. C. Mackay: `Neural network image deconvolution'. In: Maximum Entropy and Bayesian Methods. ed. by G. R. Heidbreder (Kluwer Academic Publishers 1996) pp. 319-325 http://citeseer.ist.psu.edu/tansley96neural.html More
@misc{ tansley96neural,
author = "J. Tansley and M. Oldeld and D. Mackay",
title = "Neural network image deconvolution",
text = "John E. Tansley, Martin J. Oldeld, and David J. C. Mackay: `Neural network
image deconvolution'. In: Maximum Entropy and Bayesian Methods. ed. by G.
R. Heidbreder (Kluwer Academic Publishers 1996) pp. 319-325",
year = "1996",
url = "citeseer.ist.psu.edu/tansley96neural.html" }
Citations (may not include all citations):153 A practical Bayesian framework for backpropagation networks (context) - MacKay - 1992
75 The evidence framework applied to classification networks - MacKay - 1992
25 Structural risk minimization for character recognition (context) - Guyon, Vapnik et al. - 1992
17 Image reconstruction from incomplete and noisy data (context) - Gull, Daniell - 1978
Documents on the same site (http://wol.ra.phy.cam.ac.uk/pub/mackay/README.html): More
Variational Gaussian Process Classifiers - Gibbs, MacKay (1997) (Correct)
Ensemble Learning and Evidence Maximization - MacKay (1995) (Correct)
Decoding Shortened Cyclic Codes by Belief Propagation - Wilson, MacKay (1996) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC