Results

Quick links

List of algorithms

  • Commercial systems
  • Published algorithms
  • Un-published results
  • Figures

  • whole test set
  • 'easy' set (>60x60, without any large pose, occlusion or exaggerated expression)
  • 'hard' set (>60x60, with at least one of the extreme conditions: large pose, occlusion or with exaggerated expression)
  • small faces set (<60x60)
  • large faces set (>90x90)
  • small yaw faces set (frontal)
  • medium yaw faces set (half-profile)
  • large yaw faces set (profile)
  • List of Algorithms

    Commercial systems
    [top]
    No.CodeNameInstituteDescriptionDownlaod
    1iPhotoAppleVersion 9.6curves
    2FacePP_v1MegviiFace++ online free API. Request date: 2014.10.08curves
    3FacePP_v2MegviiFace++ internal versioncurves
    4PicasaGoogleGoogle Picasa Version 3.7curves
    5GalleryMicrosoftWindows Photo Gallery Version 16.4.3528.331curves
    6EyedeaEyedea Recognition Ltd.Submit date: 2015.4.28curves
    7DenseBoxBaidu IDLSubmit date: 2015.6.5curves
    8BdFDBitdefenderSubmit date: 2015.9.19curves

    Published algorithms
    [top]
    No.CodeNamePublicationDescriptionDownload
    1ACFB. Yang, J. Yan, Z. Lei and S.Z. Li. Aggregate channel features for multi-view face detection. In IJCB, 2014.-curves
    2DPMM. Mathias, R. Benenson, M. Pedersoli, and L. Van Gool. Face detection without bells and whistles. In ECCV, 2014.Open source codescurves
    3ExemplarH. Li, Z. Lin, J. Brandt, X. Shen, and G. Hua. Efficient boosted exemplar-based face detection. In CVPR, 2014.-curves
    4HeadhunterM. Mathias, R. Benenson, M. Pedersoli, and L. Van Gool. Face detection without bells and whistles. In ECCV, 2014.Doppiacurves
    5SqrChnFtrs-5(ICF)M. Mathias, R. Benenson, M. Pedersoli, and L. Van Gool. Face detection without bells and whistles. In ECCV, 2014.Doppiacurves
    6PicoN. Markus, M. Frljak, I. S. Pandzic, J. Ahlberg, and R. Forchheimer. Object detection with pixel intensity comparisons organized in decision trees. arXiv:1305.4537, 2014.-curves
    7NPDS. Liao, A. K. Jain, and S. Z. Li. A fast and accurate unconstrained face detector. arXiv:1408.1656, 2014.-curves
    8SPMA. EL-Barkouky, A. Shalaby, A. Mahmoud, and A. Farag. Selective part models for detecting partially occluded faces in the wild. In ICIP. IEEE, 2014.-curves
    9SurfCasJ. Li and Y. Zhang. Learning SURF Cascade for Fast and Accurate Object Detection. In CVPR, 2013.Open source codescurves
    10TSMX. Zhu and D. Ramanan. Face detection, pose estimation, and landmark localization in the wild. In CVPR, 2012.Open source codescurves
    11VJP. Viola and M. J. Jones. Robust real-time face detection. In IJCV. IEEE, 2004.OpenCVcurves
    12W.S.BoostZ. Kalal, J. Matas, and K. Mikolajczyk. Weighted sampling for largescale boosting. In BMVC, 2008.Open source codescurves
    13MBLBPL. Zhang, R. Chu, S. Xiang, S. Liao, and S. Z. Li. Face detection based on multi-block lbp representation. In Advances in biometrics. Springer, 2007.-curves
    14JDAD. Chen, S. Ren, Y. Wei, X. Cao, and J. Sun. Joint Cascade Face Detection and Alignment. ECCV, 2014.-curves
    15DDFDS. S. Farfade, M. Saberian, and L-J Li. Multi-view Face Detection Using Deep Convolutional Neural Networks. ICMR, 2015.Yahoo! Inc.curves

    Note:
    Algorithms No. 9, 10, 12 are tested by ourselves using open source codes released by the original authors. We appreciate that these authors update their results.
    More details please refer to our evaluation paper.

    Un-published results
    [top]
    No.CodeNameDescriptionDownload
    1VJ-hybVJ hybridcurves
    2B-DATDPM basedcurves
    3SZUShenzhen Universitycurves

    Figures

    whole test set
    [top]

    [pdf]
    Whole test set

    'easy' set
    [top]

    [pdf]
    Easy faces

    'hard' set
    [top]

    [pdf]
    Hard faces

    small faces set
    [top]

    [pdf]
    Small faces

    large faces set
    [top]

    [pdf]
    Large faces

    small yaw faces set
    [top]

    [pdf]
    Small yaw faces

    medium yaw faces set
    [top]

    [pdf]
    Medium yaw faces

    large yaw faces set
    [top]

    [pdf]
    Large yaw faces

    News!

    29/9/15: We add fine-grained results with regard to different views, check it out at Results page!

    13/5/15: MALF is now a public benchmark. New submissions are always welcome!

    13/3/15: Curves data available!

    29/1/15: FG2015 Evaluation finished! 21 state-of-the-art algorithms are evaluated!

    10/9/14: Dataset upgraded!

    13/4/14: This face detection evaluation is part of the evaluations in FG2015.

    Contact us

    Zhen Lei: zlei[at]nlpr.ia.ac.cn
    Bin Yang: yb.derek[at]gmail.com
    Junjie Yan: yanjjie[at]gmail.com