Impact of eye detection error on face recognition performance

Abhishek Dutta*, Manuel Günther, Laurent El Shafey, Sebastien Marcel, Raymond Veldhuis, Luuk Spreeuwers

*Corresponding author for this work

    Research output: Contribution to journalArticleAcademicpeer-review

    9 Citations (Scopus)
    9 Downloads (Pure)

    Abstract

    The locations of the eyes are the most commonly used features to perform face normalisation (i.e. alignment of facial features), which is an essential preprocessing stage of many face recognition systems. In this study, the authors study the sensitivity of open source implementations of five face recognition algorithms to misalignment caused by eye localisation errors. They investigate the ambiguity in the location of the eyes by comparing the difference between two independent manual eye annotations. They also study the error characteristics of automatic eye detectors present in two commercial face recognition systems. Furthermore, they explore the impact of using different eye detectors for training/enrolment and query phases of a face recognition system. These experiments provide an insight into the influence of eye localisation errors on the performance of face recognition systems and recommend a strategy for the design of training and test sets of a face recognition algorithm.
    Original languageEnglish
    Pages (from-to)137-150
    Number of pages14
    JournalIET biometrics
    Volume4
    Issue number3
    DOIs
    Publication statusE-pub ahead of print/First online - 1 Sept 2015

    Keywords

    • query phases
    • eye detection
    • eye localisation errors
    • open source implementations
    • error characteristics
    • facial feature alignment
    • face normalisation
    • face recognition algorithms
    • face recognition performance
    • commercial face recognition systems
    • manual eye annotations
    • automatic eye detectors
    • 2023 OA procedure

    Fingerprint

    Dive into the research topics of 'Impact of eye detection error on face recognition performance'. Together they form a unique fingerprint.

    Cite this