TR2011-074

Fully Automatic Pose-Invariant Face Recognition via 3D Pose Normalization


    •  Asthana, A.; Marks, T.K.; Jones, M.J.; Tieu, K.H.; Rohith, M., "Fully Automatic Pose-Invariant Face Recognition via 3D Pose Normalization", IEEE International Conference on Computer Vision (ICCV), DOI: 10.1109/ICCV.2011.6126336, November 2011, pp. 937-944.
      BibTeX Download PDF
      • @inproceedings{Asthana2011nov,
      • author = {Asthana, A. and Marks, T.K. and Jones, M.J. and Tieu, K.H. and Rohith, M.},
      • title = {Fully Automatic Pose-Invariant Face Recognition via 3D Pose Normalization},
      • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
      • year = 2011,
      • pages = {937--944},
      • month = nov,
      • doi = {10.1109/ICCV.2011.6126336},
      • url = {http://www.merl.com/publications/TR2011-074}
      • }
  • MERL Contacts:
  • Research Area:

    Computer Vision


An ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to match one or more of these goals. In this paper, we present a fully automatic system for pose-invariant face recognition that not only meets these requirements but also outperforms other comparable methods. We propose a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system. The current system can handle 3D pose variation up to +-45 in yaw and +-30 in pitch angles. Recognition experiments were conducted on the USF 3D, Multi-PIE, CMU-PIE, FERET, and FacePix databases. Our system not only shows excellent generalization by achieving high accuracy on all 5 databases but also outperforms other methods convincingly.