Object detection and recognition using structured dimensionality reduction

Ran Sharon, Joseph M. Francos, Rami R. Hagege

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

Abstract

Assume we have a set of observations (for example, images) of different objects, each undergoing a different geometric deformation, yet all the deformations belong to the same family of deformations, Q. As a result of the action of Q, the set of different realizations for each object is generally a manifold in the space of observations. In cases where Q admits a finite dimensional representation, there is a mapping from the space of observations to a low dimensional linear subspace. Under this mapping, observations from the same manifold are mapped to the same subspace, as detailed below.

Original languageAmerican English
Title of host publication2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings
Pages619-620
Number of pages2
DOIs
StatePublished - 1 Dec 2013
Event2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Austin, TX, United States
Duration: 3 Dec 20135 Dec 2013

Publication series

Name2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings

Conference

Conference2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013
Country/TerritoryUnited States
CityAustin, TX
Period3/12/135/12/13

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Object detection and recognition using structured dimensionality reduction'. Together they form a unique fingerprint.

Cite this