Skip to content

Research at St Andrews

Reimagining the central challenge of face recognition: turning a problem into an advantage

Research output: Contribution to journalArticle

Open Access Status

  • Embargoed (until 22/06/19)

Author(s)

School/Research organisations

Abstract

High inter-personal similarity has been universally acknowledged as the principal challenge of automatic face recognition since the earliest days of research in this area. The challenge is particularly prominent when images or videos are acquired in largely unconstrained conditions ‘in the wild’, and intra-personal variability due to illumination, pose, occlusions, and a variety of other confounds is extreme. Counter to the general consensus and intuition, in this paper I demonstrate that in some contexts, high inter-personal similarity can be used to advantage, i.e. it can help improve recognition performance. I start by a theoretical introduction of this key conceptual novelty which I term ‘quasi-transitive similarity’, describe an approach that implements it in practice, and demonstrate its effectiveness empirically. The results on a most challenging real-world data set show impressive performance, and open avenues to future research on different technical approaches which make use of this novel idea.
Close

Details

Original languageEnglish
Pages (from-to)388-400
Number of pages13
JournalPattern Recognition
Volume83
Early online date22 Jun 2018
DOIs
StateE-pub ahead of print - 22 Jun 2018

    Research areas

  • Meta-algorithm, Paradigm change, Retrieval, Intra-class, Inter-class, Similarity, Dissimilarity

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Discovering topic structures of a temporally evolving document corpus

    Beykikhoshk, A., Arandelovic, O., Phung, D. & Venkatesh, S. Jun 2018 In : Knowledge and Information Systems. 55, 3, p. 599-632 34 p.

    Research output: Contribution to journalArticle

  2. Machine learning based prediction of consumer purchasing decisions: the evidence and its significance

    Stubseid, S. & Arandelovic, O. 2 Feb 2018 Proceedings AI and Marketing Science workshop at AAAI-2018. 7 p.

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

  3. Baseline fusion for image an pattern recognition - what not to do (and how to do better)

    Arandelovic, O. Dec 2017 In : Journal of Imaging. 3, 4, 16 p., 44

    Research output: Contribution to journalArticle

Related by journal

  1. Hallucinating optimal high-dimensional subspaces

    Arandelovic, O. 2014 In : Pattern Recognition. 47, 8, p. 2662-2672 11 p.

    Research output: Contribution to journalArticle

  2. Infrared face recognition: A comprehensive review of methodologies and databases

    Shoja Ghiass, R., Arandelovic, O., Bendada, A. & Maldague, X. 2014 In : Pattern Recognition. 47, 9, p. 2807-2824 18 p.

    Research output: Contribution to journalArticle

  3. Achieving robust face recognition from video by combining a weak photometric model and a learnt generic face invariant

    Arandelovic, O. & Cipolla, R. Jan 2013 In : Pattern Recognition. 46, 1, p. 9-23 15 p.

    Research output: Contribution to journalArticle

ID: 253334065