Local jet feature space framework for image processing and representation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a unified framework for processing and representing images using a feature space related to local similarity. The visual data is represented by the versatile multiscale local jet feature space, possibly reduced by vector quantisation and/or represented by data structures enabling efficient nearest neighbours search (e.g. kd-trees). We demonstrate the interest of the local jet feature space processing through three fundamental low level tasks: noise reduction, motion estimation and background modelling/subtraction. We also show the potential of the framework in terms of higher level visual representation (e.g. recognition/retrieval).

Original languageEnglish
Title of host publicationProceedings - 7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011
Pages261-268
Number of pages8
DOIs
Publication statusPublished - 1 Dec 2011
Event7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011 - Dijon, France
Duration: 28 Nov 20111 Dec 2011

Publication series

NameProceedings - 7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011

Conference

Conference7th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2011
Country/TerritoryFrance
CityDijon
Period28/11/111/12/11

Keywords

  • Background modelling
  • Multiscale local jets
  • Nearest neighbours
  • Non local means
  • Optical flow
  • Similarity space
  • Vision framework

Fingerprint

Dive into the research topics of 'Local jet feature space framework for image processing and representation'. Together they form a unique fingerprint.

Cite this