Restoration and recognition in a loop

Mithun Das Gupta, Shyamsundar Rajaram, Nemanja Petrovic, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages638-644
Number of pages7
ISBN (Print)0769523722, 9780769523729
DOIs
StatePublished - 2005
Externally publishedYes
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: Jun 20 2005Jun 25 2005

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeI

Other

Other2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Country/TerritoryUnited States
CitySan Diego, CA
Period6/20/056/25/05

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Restoration and recognition in a loop'. Together they form a unique fingerprint.

Cite this