Derivative Variation Pattern for Illumination-Invariant Image Representation

M. Tavakolian, F. Hajati, Ajmal Mian, Y. Gao, S. Gheisari

    Research output: Chapter in Book/Conference paperConference paper

    226 Downloads (Pure)

    Abstract

    This paper presents a novel image descriptor called Derivative Variation Pattern (DVP) and its application to face and palmprint recognition. DVP captures image variations in both the frequency and the spatial domains. The effects of uncontrolled illumination are compensated in the frequency domain by discarding the illumination affected frequencies. Image pixels are encoded as binary patterns based on the higher-order spatial derivatives computed in the spatial domain. The proposed descriptor was evaluated on the Extended Yale-B and FERET face databases, and the PolyU palmprint database. Experimental results demonstrate the effectiveness of the DVP descriptor in both the face and the palmprint recognition tasks under uncontrolled illuminations.
    Original languageEnglish
    Title of host publicationProceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013
    Place of PublicationAustralia
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages4210-4214
    ISBN (Print)9781479923410
    DOIs
    Publication statusPublished - Sep 2013
    Event20th IEEE International Conference on Image Processing - Melbourne, Australia, Melbourne, Australia
    Duration: 15 Sep 201318 Sep 2013

    Conference

    Conference20th IEEE International Conference on Image Processing
    Abbreviated titleICIP
    CountryAustralia
    CityMelbourne
    Period15/09/1318/09/13

    Fingerprint

    Lighting
    Palmprint recognition
    Derivatives
    Face recognition
    Pixels

    Cite this

    Tavakolian, M., Hajati, F., Mian, A., Gao, Y., & Gheisari, S. (2013). Derivative Variation Pattern for Illumination-Invariant Image Representation. In Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013 (pp. 4210-4214). Australia: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2013.6738867
    Tavakolian, M. ; Hajati, F. ; Mian, Ajmal ; Gao, Y. ; Gheisari, S. / Derivative Variation Pattern for Illumination-Invariant Image Representation. Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013. Australia : IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 4210-4214
    @inproceedings{8ba033b171ee4119ac8a6e693527cb86,
    title = "Derivative Variation Pattern for Illumination-Invariant Image Representation",
    abstract = "This paper presents a novel image descriptor called Derivative Variation Pattern (DVP) and its application to face and palmprint recognition. DVP captures image variations in both the frequency and the spatial domains. The effects of uncontrolled illumination are compensated in the frequency domain by discarding the illumination affected frequencies. Image pixels are encoded as binary patterns based on the higher-order spatial derivatives computed in the spatial domain. The proposed descriptor was evaluated on the Extended Yale-B and FERET face databases, and the PolyU palmprint database. Experimental results demonstrate the effectiveness of the DVP descriptor in both the face and the palmprint recognition tasks under uncontrolled illuminations.",
    author = "M. Tavakolian and F. Hajati and Ajmal Mian and Y. Gao and S. Gheisari",
    year = "2013",
    month = "9",
    doi = "10.1109/ICIP.2013.6738867",
    language = "English",
    isbn = "9781479923410",
    pages = "4210--4214",
    booktitle = "Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Tavakolian, M, Hajati, F, Mian, A, Gao, Y & Gheisari, S 2013, Derivative Variation Pattern for Illumination-Invariant Image Representation. in Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013. IEEE, Institute of Electrical and Electronics Engineers, Australia, pp. 4210-4214, 20th IEEE International Conference on Image Processing , Melbourne, Australia, 15/09/13. https://doi.org/10.1109/ICIP.2013.6738867

    Derivative Variation Pattern for Illumination-Invariant Image Representation. / Tavakolian, M.; Hajati, F.; Mian, Ajmal; Gao, Y.; Gheisari, S.

    Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013. Australia : IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 4210-4214.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - Derivative Variation Pattern for Illumination-Invariant Image Representation

    AU - Tavakolian, M.

    AU - Hajati, F.

    AU - Mian, Ajmal

    AU - Gao, Y.

    AU - Gheisari, S.

    PY - 2013/9

    Y1 - 2013/9

    N2 - This paper presents a novel image descriptor called Derivative Variation Pattern (DVP) and its application to face and palmprint recognition. DVP captures image variations in both the frequency and the spatial domains. The effects of uncontrolled illumination are compensated in the frequency domain by discarding the illumination affected frequencies. Image pixels are encoded as binary patterns based on the higher-order spatial derivatives computed in the spatial domain. The proposed descriptor was evaluated on the Extended Yale-B and FERET face databases, and the PolyU palmprint database. Experimental results demonstrate the effectiveness of the DVP descriptor in both the face and the palmprint recognition tasks under uncontrolled illuminations.

    AB - This paper presents a novel image descriptor called Derivative Variation Pattern (DVP) and its application to face and palmprint recognition. DVP captures image variations in both the frequency and the spatial domains. The effects of uncontrolled illumination are compensated in the frequency domain by discarding the illumination affected frequencies. Image pixels are encoded as binary patterns based on the higher-order spatial derivatives computed in the spatial domain. The proposed descriptor was evaluated on the Extended Yale-B and FERET face databases, and the PolyU palmprint database. Experimental results demonstrate the effectiveness of the DVP descriptor in both the face and the palmprint recognition tasks under uncontrolled illuminations.

    U2 - 10.1109/ICIP.2013.6738867

    DO - 10.1109/ICIP.2013.6738867

    M3 - Conference paper

    SN - 9781479923410

    SP - 4210

    EP - 4214

    BT - Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - Australia

    ER -

    Tavakolian M, Hajati F, Mian A, Gao Y, Gheisari S. Derivative Variation Pattern for Illumination-Invariant Image Representation. In Proceedings of 20th IEEE International Conference on Image Processing (ICIP), 2013. Australia: IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 4210-4214 https://doi.org/10.1109/ICIP.2013.6738867