NEWS    MERL Researcher Tim Marks presents an invited talk at MIT Lincoln Laboratory

Date released: April 27, 2017


  •  NEWS    MERL Researcher Tim Marks presents an invited talk at MIT Lincoln Laboratory
  • Date:

    April 27, 2017

  • Where:

    Lincoln Laboratory, Massachusetts Institute of Technology

  • Description:

    MERL researcher Tim K. Marks presented an invited talk as part of the MIT Lincoln Laboratory CORE Seminar Series on Biometrics. The talk was entitled "Robust Real-Time 2D Face Alignment and 3D Head Pose Estimation."

    Abstract: Head pose estimation and facial landmark localization are key technologies, with widespread application areas including biometrics and human-computer interfaces. This talk describes two different robust real-time face-processing methods, each using a different modality of input image. The first part of the talk describes our system for 3D head pose estimation and facial landmark localization using a commodity depth sensor. The method is based on a novel 3D Triangular Surface Patch (TSP) descriptor, which is viewpoint-invariant as well as robust to noise and to variations in the data resolution. This descriptor, combined with fast nearest-neighbor lookup and a joint voting scheme, enable our system to handle arbitrary head pose and significant occlusions. The second part of the talk describes our method for face alignment, which is the localization of a set of facial landmark points in a 2D image or video of a face. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a Mixture of Invariant eXperts (MIX), where each expert learns a regression model that is specialized to a different subset of the joint space of pose and expressions. We also present a method to include deformation constraints within the discriminative alignment framework, which makes the algorithm more robust. Both our 3D head pose and 2D face alignment methods outperform the previous results on standard datasets. If permitted, I plan to end the talk with a live demonstration.

  • MERL Contact:
  • Research Area:

    Machine Learning

    •  Tuzel, C.O., Marks, T.K., Tambe, S., "Robust Face Alignment Using a Mixture of Invariant Experts", European Conference on Computer Vision (ECCV), DOI: 10.1007/​978-3-319-46454-1_50, October 2016, vol. 9909, pp. 825-841.
      BibTeX TR2016-129 PDF
      • @inproceedings{Tuzel2016oct,
      • author = {Tuzel, C. Oncel and Marks, Tim K. and Tambe, Salil},
      • title = {Robust Face Alignment Using a Mixture of Invariant Experts},
      • booktitle = {European Conference on Computer Vision (ECCV)},
      • year = 2016,
      • volume = 9909,
      • pages = {825--841},
      • month = oct,
      • doi = {10.1007/978-3-319-46454-1_50},
      • url = {https://www.merl.com/publications/TR2016-129}
      • }
    •  Papazov, C., Marks, T.K., Jones, M.J., "Real-time Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/​CVPR.2015.7299104, June 2015, pp. 4722-4730.
      BibTeX TR2015-069 PDF
      • @inproceedings{Marks2015jun,
      • author = {Papazov, C. and Marks, T.K. and Jones, M.J.},
      • title = {Real-time Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2015,
      • pages = {4722--4730},
      • month = jun,
      • publisher = {IEEE},
      • doi = {10.1109/CVPR.2015.7299104},
      • url = {https://www.merl.com/publications/TR2015-069}
      • }