Personal re-identification using rank-based manifold ranking

Cheng Ta Hsieh, Kuo Chin Fan, Chin Chun Han

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

Abstract

In this paper, a rank-based manifold ranking (MR) algorithm is proposed for personal re-identification. In general cases, L1 norm, L2 norm, or cos production metrics are frequently adopted for distance or similarity calculation with a heat kernel function. However, outliers in the distance-based scheme always impact the identification results even though the number of outliers is few. A rank-based weighting scheme is adopted in the MR algorithm instead of the distance-based metric. A benchmark dataset of video surveillance is evaluated. The experimental results are given to show the feasibility of the proposed method.

Original languageEnglish
Title of host publicationICCST 2015 - The 49th Annual IEEE International Carnahan Conference on Security Technology
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages391-394
Number of pages4
ISBN (Electronic)9781479986910
DOIs
StatePublished - 21 Jan 2016
Event49th Annual IEEE International Carnahan Conference on Security Technology, ICCST 2015 - Taipei, Taiwan
Duration: 21 Sep 201524 Sep 2015

Publication series

NameProceedings - International Carnahan Conference on Security Technology
Volume2015-January
ISSN (Print)1071-6572

Conference

Conference49th Annual IEEE International Carnahan Conference on Security Technology, ICCST 2015
Country/TerritoryTaiwan
CityTaipei
Period21/09/1524/09/15

Keywords

  • manifold ranking
  • order-based metric
  • person re-identification
  • video surveillance

Fingerprint

Dive into the research topics of 'Personal re-identification using rank-based manifold ranking'. Together they form a unique fingerprint.

Cite this