Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection

J. Orozco, B. Martinez, Maja Pantic

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

    76 Downloads (Pure)

    Abstract

    In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.
    Original languageUndefined
    Title of host publicationProceedings of the IEEE International Conference on Image Processing, ICIP 2013
    Place of PublicationUSA
    PublisherIEEE Computer Society
    PagesWA.L5.5
    Number of pages5
    ISBN (Print)not assigned
    Publication statusPublished - Sep 2013

    Publication series

    Name
    PublisherIEEE Computer Society

    Keywords

    • EWI-24551
    • HMI-HF: Human Factors
    • FDDB database
    • IR-95219
    • AFLW database
    • Multi-View Face Detection
    • METIS-310008
    • Cascade Deformable Models

    Cite this

    Orozco, J., Martinez, B., & Pantic, M. (2013). Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection. In Proceedings of the IEEE International Conference on Image Processing, ICIP 2013 (pp. WA.L5.5). USA: IEEE Computer Society.
    Orozco, J. ; Martinez, B. ; Pantic, Maja. / Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection. Proceedings of the IEEE International Conference on Image Processing, ICIP 2013. USA : IEEE Computer Society, 2013. pp. WA.L5.5
    @inproceedings{e6c7906a2e28400a9540ca65b36505e9,
    title = "Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection",
    abstract = "In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.",
    keywords = "EWI-24551, HMI-HF: Human Factors, FDDB database, IR-95219, AFLW database, Multi-View Face Detection, METIS-310008, Cascade Deformable Models",
    author = "J. Orozco and B. Martinez and Maja Pantic",
    year = "2013",
    month = "9",
    language = "Undefined",
    isbn = "not assigned",
    publisher = "IEEE Computer Society",
    pages = "WA.L5.5",
    booktitle = "Proceedings of the IEEE International Conference on Image Processing, ICIP 2013",
    address = "United States",

    }

    Orozco, J, Martinez, B & Pantic, M 2013, Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection. in Proceedings of the IEEE International Conference on Image Processing, ICIP 2013. IEEE Computer Society, USA, pp. WA.L5.5.

    Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection. / Orozco, J.; Martinez, B.; Pantic, Maja.

    Proceedings of the IEEE International Conference on Image Processing, ICIP 2013. USA : IEEE Computer Society, 2013. p. WA.L5.5.

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

    TY - GEN

    T1 - Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection

    AU - Orozco, J.

    AU - Martinez, B.

    AU - Pantic, Maja

    PY - 2013/9

    Y1 - 2013/9

    N2 - In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.

    AB - In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.

    KW - EWI-24551

    KW - HMI-HF: Human Factors

    KW - FDDB database

    KW - IR-95219

    KW - AFLW database

    KW - Multi-View Face Detection

    KW - METIS-310008

    KW - Cascade Deformable Models

    M3 - Conference contribution

    SN - not assigned

    SP - WA.L5.5

    BT - Proceedings of the IEEE International Conference on Image Processing, ICIP 2013

    PB - IEEE Computer Society

    CY - USA

    ER -

    Orozco J, Martinez B, Pantic M. Empirical Analysis of Cascade Deformable Models for Multi-View Face Detection. In Proceedings of the IEEE International Conference on Image Processing, ICIP 2013. USA: IEEE Computer Society. 2013. p. WA.L5.5