Automatic Eye Detection Error as a Predictor of Face Recognition Performance

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

    11 Citations (Scopus)
    14 Downloads (Pure)

    Abstract

    Various facial image quality parameters like pose, illumination, noise, resolution, etc are known to be a predictor of face recognition performance. However, there still remain many other properties of facial images that are not captured by the existing quality parameters. In this paper, we propose a novel image quality parameter called the Automatic Eye Detection Error (AEDE) which measures the difference between manually located and automatically detected eye coordinates. Our experiment results carried out using FaceVACS recognition system and the MultiPIE dataset show that AEDE is indeed a predictor of face recognition performance.
    Original languageEnglish
    Title of host publication35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux
    Subtitle of host publicationEindhoven, The Netherlands, May 12-13, 2014
    Place of PublicationEindhoven
    PublisherWerkgemeenschap voor Informatie- en Communicatietheorie (WIC)
    Pages89-96
    Number of pages8
    ISBN (Print)978-90-365-3383-6
    Publication statusPublished - May 2014
    Event35th WIC Symposium on Information Theory in the Benelux 2014 - Eindhoven, Netherlands
    Duration: 12 May 201413 May 2014
    Conference number: 35

    Conference

    Conference35th WIC Symposium on Information Theory in the Benelux 2014
    CountryNetherlands
    CityEindhoven
    Period12/05/1413/05/14

    Fingerprint

    Error detection
    Face recognition
    Image quality
    Lighting
    Experiments

    Keywords

    • SCS-Safety
    • Performance Prediction
    • EWI-24813
    • IR-91485
    • Face Recognition
    • METIS-305908
    • Eye Detection Error

    Cite this

    Dutta, A., Veldhuis, R., & Spreeuwers, L. (2014). Automatic Eye Detection Error as a Predictor of Face Recognition Performance. In 35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux: Eindhoven, The Netherlands, May 12-13, 2014 (pp. 89-96). Eindhoven: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC).
    Dutta, Abhishek ; Veldhuis, Raymond ; Spreeuwers, Luuk. / Automatic Eye Detection Error as a Predictor of Face Recognition Performance. 35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux: Eindhoven, The Netherlands, May 12-13, 2014. Eindhoven : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2014. pp. 89-96
    @inproceedings{ea3e08f348144fe1a083759ff65a53ef,
    title = "Automatic Eye Detection Error as a Predictor of Face Recognition Performance",
    abstract = "Various facial image quality parameters like pose, illumination, noise, resolution, etc are known to be a predictor of face recognition performance. However, there still remain many other properties of facial images that are not captured by the existing quality parameters. In this paper, we propose a novel image quality parameter called the Automatic Eye Detection Error (AEDE) which measures the difference between manually located and automatically detected eye coordinates. Our experiment results carried out using FaceVACS recognition system and the MultiPIE dataset show that AEDE is indeed a predictor of face recognition performance.",
    keywords = "SCS-Safety, Performance Prediction, EWI-24813, IR-91485, Face Recognition, METIS-305908, Eye Detection Error",
    author = "Abhishek Dutta and Raymond Veldhuis and Luuk Spreeuwers",
    year = "2014",
    month = "5",
    language = "English",
    isbn = "978-90-365-3383-6",
    pages = "89--96",
    booktitle = "35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux",
    publisher = "Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)",
    address = "Netherlands",

    }

    Dutta, A, Veldhuis, R & Spreeuwers, L 2014, Automatic Eye Detection Error as a Predictor of Face Recognition Performance. in 35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux: Eindhoven, The Netherlands, May 12-13, 2014. Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), Eindhoven, pp. 89-96, 35th WIC Symposium on Information Theory in the Benelux 2014, Eindhoven, Netherlands, 12/05/14.

    Automatic Eye Detection Error as a Predictor of Face Recognition Performance. / Dutta, Abhishek; Veldhuis, Raymond; Spreeuwers, Luuk.

    35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux: Eindhoven, The Netherlands, May 12-13, 2014. Eindhoven : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2014. p. 89-96.

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

    TY - GEN

    T1 - Automatic Eye Detection Error as a Predictor of Face Recognition Performance

    AU - Dutta, Abhishek

    AU - Veldhuis, Raymond

    AU - Spreeuwers, Luuk

    PY - 2014/5

    Y1 - 2014/5

    N2 - Various facial image quality parameters like pose, illumination, noise, resolution, etc are known to be a predictor of face recognition performance. However, there still remain many other properties of facial images that are not captured by the existing quality parameters. In this paper, we propose a novel image quality parameter called the Automatic Eye Detection Error (AEDE) which measures the difference between manually located and automatically detected eye coordinates. Our experiment results carried out using FaceVACS recognition system and the MultiPIE dataset show that AEDE is indeed a predictor of face recognition performance.

    AB - Various facial image quality parameters like pose, illumination, noise, resolution, etc are known to be a predictor of face recognition performance. However, there still remain many other properties of facial images that are not captured by the existing quality parameters. In this paper, we propose a novel image quality parameter called the Automatic Eye Detection Error (AEDE) which measures the difference between manually located and automatically detected eye coordinates. Our experiment results carried out using FaceVACS recognition system and the MultiPIE dataset show that AEDE is indeed a predictor of face recognition performance.

    KW - SCS-Safety

    KW - Performance Prediction

    KW - EWI-24813

    KW - IR-91485

    KW - Face Recognition

    KW - METIS-305908

    KW - Eye Detection Error

    M3 - Conference contribution

    SN - 978-90-365-3383-6

    SP - 89

    EP - 96

    BT - 35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux

    PB - Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)

    CY - Eindhoven

    ER -

    Dutta A, Veldhuis R, Spreeuwers L. Automatic Eye Detection Error as a Predictor of Face Recognition Performance. In 35rd WIC Symposium on Information Theory in the Benelux and The 4th WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux: Eindhoven, The Netherlands, May 12-13, 2014. Eindhoven: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC). 2014. p. 89-96