Face Recognition

Overview

Detecting and identifying human faces in an image is a task that computers find much more challenging than human beings. The performance of existing face recognizers is not acceptable for images taken under uncontrolled settings with large variations in parameters such as pose, lighting, and expression. Modeling the distribution of appearances of these face images has not been very effective. In this project, we explore the utility of hyper-feature models for modeling the difference in appearance of two face images. The details of the hyper-feature models can be found here (project page at UC-Berkeley). The following figure demonstrates the working of a hyper-feature based face recognizer.


hyper face recog

Faculty


Graduate Students


Collaborators


References

  • Gary B. Huang, Honglak Lee, and Erik Learned-Miller.
    Learning Hierarchical Representations for Face Verification.
    Computer Vision and Pattern Recognition (CVPR), 2012.
    [pdf]
    [webpage]
  • Gary B. Huang, Michael J. Jones, and Erik Learned-Miller.
    LFW Results Using a Combined Nowak Plus MERL Recognizer.
    Faces in Real-Life Images Workshop in European Conference on Computer Vision (ECCV), 2008.
    [pdf]
  • Gary B. Huang, Marwan Mattar, Tamara Berg, and Erik Learned-Miller.
    Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments.
    Faces in Real-Life Images Workshop in European Conference on Computer Vision (ECCV), 2008.
    [pdf]
  • Gary B. Huang, Manjunath Narayana, and Erik Learned-Miller.
    Towards unconstrained face recognition.
    The Sixth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision IEEE CVPR, 2008.
    [pdf]
  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Learning to locate informative features for visual identification.
    To appear International Journal of Computer Vision: Special Issue on Learning and Vision, 2007.
    [pdf]
  • Vidit Jain, Erik Learned-Miller, and Andrew McCallum.
    People-LDA: Anchoring topics to people using face recognition.
    International Conference on Computer Vision (ICCV), 2007.
    [pdf] [project page]
  • Vidit Jain, Andras Ferencz, and Erik Learned-Miller.
    Discriminative training of hyper-feature models for object identification.
    Proceedings of the British Machine Vision Conference (BMVC), Volume 1, pp. 357-366, 2006.
    [pdf]