Restoration and recognition in a loop

In this paper we present a novel learning based method for restoring and recognizing images of digits that have been blurred using an unknown kernel. The novelty of our work is an iterative loop that alternates between recognition and restoration stages. In the restoration stage we model the image a...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 638 - 644 vol. 1
Main Authors Gupta, M.D., Rajaram, S., Petrovic, N., Huang, T.S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Bayesian methods
Computer vision
Image recognition
Image resolution
Image restoration
Kernel
Learning systems
Licenses
Machine learning
Wiener filter
Online AccessGet full text

Cover

More Information
Summary:In this paper we present a novel learning based method for restoring and recognizing images of digits that have been blurred using an unknown kernel. The novelty of our work is an iterative loop that alternates between recognition and restoration stages. In the restoration stage we model the image as an undirected graphical model over the image patches with the compatibility functions represented as non-parametric kernel densities. Compatibility functions are initially learned using uniform random samples from the training data. We solve the inference problem by an extended version of the non-parametric belief propagation algorithm in which we introduce the notion of partial messages. We close the loop by using the confidence scores of the recognition to non-uniformly sample from the training set in order to retrain the compatibility functions. We show experimental results on synthetic and license plate images.
ISBN:0769523722
9780769523729
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2005.302