Skip to main navigation Skip to search Skip to main content

Subspace learning via low rank projections for dimensionality reduction

  • SUNY Buffalo

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

Abstract

Subspace learning algorithms aim at finding low dimensional linear manifolds that are representative of the data at hand. In this paper we propose a semi-supervised approach that fits any given dataset to a low dimensional subspace while maintaining class separability. Our approach has no tunable parameters as against many existing subspace learning algorithms which obviates the need for cross-validation. We apply our algorithm to the problem of face recognition. We perform both qualitative as well as quantitative experiments on multiple real world datasets. For qualitative analysis we visualize the class separability of binary and multi-class projected data. For quantitative analysis, we perform classification experiments on projected data and achieve state-of-the-art results compared to popular existing dimensionality reduction methods.

Original languageEnglish
Title of host publication2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467397339
DOIs
StatePublished - Dec 19 2016
Event8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016 - Niagara Falls, United States
Duration: Sep 6 2016Sep 9 2016

Publication series

Name2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

Conference

Conference8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016
Country/TerritoryUnited States
CityNiagara Falls
Period09/6/1609/9/16

Fingerprint

Dive into the research topics of 'Subspace learning via low rank projections for dimensionality reduction'. Together they form a unique fingerprint.

Cite this