Empowering Simple Binary Classifiers for Image Set Based Face Recognition

Munawar HAYAT, Salman Khan, Mohammed Bennamoun

    Research output: Contribution to journalArticle

    10 Citations (Scopus)

    Abstract

    Face recognition from image sets has numerous real-life applications including recognition from security and surveillance systems, multi-view camera networks and personal albums. An image set is an unordered collection of images (e.g., video frames, images acquired over long term observations and personal albums) which exhibits a wide range of appearance variations. The main focus of the previously developed methods has therefore been to find a suitable representation to optimally model these variations. This paper argues that such a representation could not necessarily encode all of the information contained in the set. The paper, therefore, suggests a different approach which does not resort to a single representation of an image set. Instead, the images of the set are retained in their original form and an efficient classification strategy is developed which extends well-known simple binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers to be trained over a large number of images, the proposed approach is efficient since it trains only few binary classifiers on very few images. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for image set classification based face and object recognition on a number of challenging datasets.
    Original languageEnglish
    Pages (from-to)479-498
    Number of pages20
    JournalInternational Journal of Computer Vision
    Volume123
    Issue number3
    DOIs
    Publication statusPublished - 1 Jul 2017

    Fingerprint

    Face recognition
    Classifiers
    Object recognition
    Cameras
    Experiments

    Cite this

    HAYAT, Munawar ; Khan, Salman ; Bennamoun, Mohammed . / Empowering Simple Binary Classifiers for Image Set Based Face Recognition. In: International Journal of Computer Vision. 2017 ; Vol. 123, No. 3. pp. 479-498.
    @article{cc2935345e2d43e38452a472eee537ac,
    title = "Empowering Simple Binary Classifiers for Image Set Based Face Recognition",
    abstract = "Face recognition from image sets has numerous real-life applications including recognition from security and surveillance systems, multi-view camera networks and personal albums. An image set is an unordered collection of images (e.g., video frames, images acquired over long term observations and personal albums) which exhibits a wide range of appearance variations. The main focus of the previously developed methods has therefore been to find a suitable representation to optimally model these variations. This paper argues that such a representation could not necessarily encode all of the information contained in the set. The paper, therefore, suggests a different approach which does not resort to a single representation of an image set. Instead, the images of the set are retained in their original form and an efficient classification strategy is developed which extends well-known simple binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers to be trained over a large number of images, the proposed approach is efficient since it trains only few binary classifiers on very few images. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for image set classification based face and object recognition on a number of challenging datasets.",
    keywords = "Image set classification , Binary to multi-class classification , Object recognition, Video based face recognition , Image set classification, Binary to multi-class classification, Video based face recognition",
    author = "Munawar HAYAT and Salman Khan and Mohammed Bennamoun",
    year = "2017",
    month = "7",
    day = "1",
    doi = "10.1007/s11263-017-1000-3",
    language = "English",
    volume = "123",
    pages = "479--498",
    journal = "International Journal of Computer Vision",
    issn = "0920-5691",
    publisher = "Springer",
    number = "3",

    }

    Empowering Simple Binary Classifiers for Image Set Based Face Recognition. / HAYAT, Munawar; Khan, Salman; Bennamoun, Mohammed .

    In: International Journal of Computer Vision, Vol. 123, No. 3, 01.07.2017, p. 479-498.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Empowering Simple Binary Classifiers for Image Set Based Face Recognition

    AU - HAYAT, Munawar

    AU - Khan, Salman

    AU - Bennamoun, Mohammed

    PY - 2017/7/1

    Y1 - 2017/7/1

    N2 - Face recognition from image sets has numerous real-life applications including recognition from security and surveillance systems, multi-view camera networks and personal albums. An image set is an unordered collection of images (e.g., video frames, images acquired over long term observations and personal albums) which exhibits a wide range of appearance variations. The main focus of the previously developed methods has therefore been to find a suitable representation to optimally model these variations. This paper argues that such a representation could not necessarily encode all of the information contained in the set. The paper, therefore, suggests a different approach which does not resort to a single representation of an image set. Instead, the images of the set are retained in their original form and an efficient classification strategy is developed which extends well-known simple binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers to be trained over a large number of images, the proposed approach is efficient since it trains only few binary classifiers on very few images. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for image set classification based face and object recognition on a number of challenging datasets.

    AB - Face recognition from image sets has numerous real-life applications including recognition from security and surveillance systems, multi-view camera networks and personal albums. An image set is an unordered collection of images (e.g., video frames, images acquired over long term observations and personal albums) which exhibits a wide range of appearance variations. The main focus of the previously developed methods has therefore been to find a suitable representation to optimally model these variations. This paper argues that such a representation could not necessarily encode all of the information contained in the set. The paper, therefore, suggests a different approach which does not resort to a single representation of an image set. Instead, the images of the set are retained in their original form and an efficient classification strategy is developed which extends well-known simple binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers to be trained over a large number of images, the proposed approach is efficient since it trains only few binary classifiers on very few images. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for image set classification based face and object recognition on a number of challenging datasets.

    KW - Image set classification

    KW - Binary to multi-class classification

    KW - Object recognition

    KW - Video based face recognition

    KW - Image set classification

    KW - Binary to multi-class classification

    KW - Video based face recognition

    UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85014035325&origin=resultslist&sort=plf-f&src=s&st1=Empowering+Simple+Binary+Classifiers+for+Image+Set+Based+Face+Recognition&st2=&sid=189a9c0c3cb2a7e2179c6a997a2a5b90&sot=b&sdt=b&sl=88&s=TITLE-ABS-KEY%28Empowering+Simple+Binary+Classifiers+for+Image+Set+Based+Face+Recognition%29&relpos=0&citeCnt=0&searchTerm=

    UR - http://www.mendeley.com/research/empowering-simple-binary-classifiers-image-set-based-face-recognition

    U2 - 10.1007/s11263-017-1000-3

    DO - 10.1007/s11263-017-1000-3

    M3 - Article

    VL - 123

    SP - 479

    EP - 498

    JO - International Journal of Computer Vision

    JF - International Journal of Computer Vision

    SN - 0920-5691

    IS - 3

    ER -