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)


School/Research organisations


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.


Original languageEnglish
Pages (from-to)388-400
Number of pages13
JournalPattern Recognition
Early online date22 Jun 2018
Publication statusPublished - Nov 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. A more principled use of the p-value? Not so fast: a critique of Colquhoun's argument

    Arandelović, O., 15 May 2019, In : Royal Society Open Science. 6, 5, 5 p., 181519.

    Research output: Contribution to journalArticle

  2. Highly accurate and fully automatic 3D head pose estimation and eye gaze estimation using RGB-D sensors and 3D morphable models

    Ghiass, R. S., Arandjelovic, O. & Laurendeau, D., 5 Dec 2018, In : Sensors. 18, 12, 21 p., 4280.

    Research output: Contribution to journalArticle

Related by journal

  1. Efficient and accurate set-based registration of time-separated aerial images

    Arandelovic, O., Pham, D. S. & Venkatesh, S., 1 Nov 2015, In : Pattern Recognition. 48, 11, p. 3466-3476 11 p.

    Research output: Contribution to journalArticle

  2. Hallucinating optimal high-dimensional subspaces

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

    Research output: Contribution to journalArticle

  3. 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

  4. 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