Fast Localization of Facial Landmark Points

Abstract

Localization of salient facial landmark points, such as eye corners or the tip of the nose, is still considered a challenging computer vision problem despite recent efforts. This is especially evident in unconstrained environments, i.e., in the presence of background clutter and large head pose variations. Most methods that achieve state-of-the-art accuracy are slow, and, thus, have limited applications. We describe a method that can accurately estimate the positions of relevant facial landmarks in real-time even on hardware with limited processing power, such as mobile devices. This is achieved with a sequence of estimators based on ensembles of regression trees. The trees use simple pixel intensity comparisons in their internal nodes and this makes them able to process image regions very fast. We test the developed system on several publicly available datasets and analyse its processing speed on various devices. Experimental results show that our method has practical value.

Files

Full Paper as PDF

BibTeX Citation

DOI

10.20532/ccvw.2014.0001

https://doi.org/10.20532/ccvw.2014.0001

BibTeX

@InProceedings{10.20532/ccvw.2014.0001,
  author =       {Nenad Marku{\v s} and Miroslav Frljak and Pand{\v
                  z}i{\' c}, Igor Sunday and J{\" o}rgen Ahlberg and
                  Robert Forchheimer},
  title =        {Fast Localization of Facial Landmark Points},
  booktitle =    {Proceedings of the Croatian Compter Vision Workshop,
                  Year 2},
  pages =        {39-43},
  year =         2014,
  editor =       {Lon{\v c}ari{\' c}, Sven and Suba{\v s}i{\' c},
                  Marko},
  address =      {Zagreb},
  month =        {September},
  organization = {Center of Excellence for Computer Vision},
  publisher =    {University of Zagreb},
  abstract =     {Localization of salient facial landmark points, such
                  as eye corners or the tip of the nose, is still
                  considered a challenging computer vision problem
                  despite recent efforts. This is especially evident
                  in unconstrained environments, i.e., in the presence
                  of background clutter and large head pose
                  variations. Most methods that achieve
                  state-of-the-art accuracy are slow, and, thus, have
                  limited applications. We describe a method that can
                  accurately estimate the positions of relevant facial
                  landmarks in real-time even on hardware with limited
                  processing power, such as mobile devices. This is
                  achieved with a sequence of estimators based on
                  ensembles of regression trees. The trees use simple
                  pixel intensity comparisons in their internal nodes
                  and this makes them able to process image regions
                  very fast. We test the developed system on several
                  publicly available datasets and analyse its
                  processing speed on various devices. Experimental
                  results show that our method has practical value.},
  doi =          {10.20532/ccvw.2014.0001},
  url =          {https://doi.org/10.20532/ccvw.2014.0001}
}