Subspace-Based Holistic Registration for Low-Resolution Facial Images

    Research output: Contribution to journalArticleAcademicpeer-review

    2 Citations (Scopus)
    63 Downloads (Pure)

    Abstract

    Subspace-based holistic registration is introduced as an alternative to landmark-based face registration, which has a poor performance on low-resolution images, as obtained in camera surveillance applications. The proposed registration method finds the alignment by maximizing the similarity score between a probe and a gallery image. We use a novel probabilistic framework for both user-independent as well as user-specific face registration. The similarity is calculated using the probability that the face image is correctly aligned in a face subspace, but additionally we take the probability into account that the face is misaligned based on the residual error in the dimensions perpendicular to the face subspace. We perform extensive experiments on the FRGCv2 database to evaluate the impact that the face registration methods have on face recognition. Subspace-based holistic registration on low-resolution images can improve face recognition in comparison with landmark-based registration on high-resolution images. The performance of the tested face recognition methods after subspace-based holistic registration on a low-resolution version of the FRGC database is similar to that after manual registration.
    Original languageUndefined
    Pages (from-to)1-14
    Number of pages14
    JournalEURASIP journal on advances in signal processing
    Volume2010
    DOIs
    Publication statusPublished - 14 Jul 2010

    Keywords

    • SCS-Safety
    • Face Recognition
    • Face Registration
    • IR-74239
    • Low Resolution
    • EWI-18678
    • METIS-271100
    • Holistic Registration

    Cite this

    @article{a1f09fa2f9124bb5a1cb7ba1f8622407,
    title = "Subspace-Based Holistic Registration for Low-Resolution Facial Images",
    abstract = "Subspace-based holistic registration is introduced as an alternative to landmark-based face registration, which has a poor performance on low-resolution images, as obtained in camera surveillance applications. The proposed registration method finds the alignment by maximizing the similarity score between a probe and a gallery image. We use a novel probabilistic framework for both user-independent as well as user-specific face registration. The similarity is calculated using the probability that the face image is correctly aligned in a face subspace, but additionally we take the probability into account that the face is misaligned based on the residual error in the dimensions perpendicular to the face subspace. We perform extensive experiments on the FRGCv2 database to evaluate the impact that the face registration methods have on face recognition. Subspace-based holistic registration on low-resolution images can improve face recognition in comparison with landmark-based registration on high-resolution images. The performance of the tested face recognition methods after subspace-based holistic registration on a low-resolution version of the FRGC database is similar to that after manual registration.",
    keywords = "SCS-Safety, Face Recognition, Face Registration, IR-74239, Low Resolution, EWI-18678, METIS-271100, Holistic Registration",
    author = "B.J. Boom and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.}",
    note = "Article ID 591412",
    year = "2010",
    month = "7",
    day = "14",
    doi = "10.1155/2010/591412",
    language = "Undefined",
    volume = "2010",
    pages = "1--14",
    journal = "EURASIP journal on advances in signal processing",
    issn = "1687-6172",
    publisher = "Springer",

    }

    Subspace-Based Holistic Registration for Low-Resolution Facial Images. / Boom, B.J.; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

    In: EURASIP journal on advances in signal processing, Vol. 2010, 14.07.2010, p. 1-14.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Subspace-Based Holistic Registration for Low-Resolution Facial Images

    AU - Boom, B.J.

    AU - Spreeuwers, Lieuwe Jan

    AU - Veldhuis, Raymond N.J.

    N1 - Article ID 591412

    PY - 2010/7/14

    Y1 - 2010/7/14

    N2 - Subspace-based holistic registration is introduced as an alternative to landmark-based face registration, which has a poor performance on low-resolution images, as obtained in camera surveillance applications. The proposed registration method finds the alignment by maximizing the similarity score between a probe and a gallery image. We use a novel probabilistic framework for both user-independent as well as user-specific face registration. The similarity is calculated using the probability that the face image is correctly aligned in a face subspace, but additionally we take the probability into account that the face is misaligned based on the residual error in the dimensions perpendicular to the face subspace. We perform extensive experiments on the FRGCv2 database to evaluate the impact that the face registration methods have on face recognition. Subspace-based holistic registration on low-resolution images can improve face recognition in comparison with landmark-based registration on high-resolution images. The performance of the tested face recognition methods after subspace-based holistic registration on a low-resolution version of the FRGC database is similar to that after manual registration.

    AB - Subspace-based holistic registration is introduced as an alternative to landmark-based face registration, which has a poor performance on low-resolution images, as obtained in camera surveillance applications. The proposed registration method finds the alignment by maximizing the similarity score between a probe and a gallery image. We use a novel probabilistic framework for both user-independent as well as user-specific face registration. The similarity is calculated using the probability that the face image is correctly aligned in a face subspace, but additionally we take the probability into account that the face is misaligned based on the residual error in the dimensions perpendicular to the face subspace. We perform extensive experiments on the FRGCv2 database to evaluate the impact that the face registration methods have on face recognition. Subspace-based holistic registration on low-resolution images can improve face recognition in comparison with landmark-based registration on high-resolution images. The performance of the tested face recognition methods after subspace-based holistic registration on a low-resolution version of the FRGC database is similar to that after manual registration.

    KW - SCS-Safety

    KW - Face Recognition

    KW - Face Registration

    KW - IR-74239

    KW - Low Resolution

    KW - EWI-18678

    KW - METIS-271100

    KW - Holistic Registration

    U2 - 10.1155/2010/591412

    DO - 10.1155/2010/591412

    M3 - Article

    VL - 2010

    SP - 1

    EP - 14

    JO - EURASIP journal on advances in signal processing

    JF - EURASIP journal on advances in signal processing

    SN - 1687-6172

    ER -