Department of Computer Science Technische Universitaet Muenchen
Home People Teaching Research Publications Info Sitemap
Research | Publications | Teaching | Miscellaneous | Contact

Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

Matthias Wimmer, Christoph Mayer, Freek Stulp, and Bernd Radig. Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components. In Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA), held in conjunction with CVPR, 2008. Non-archival.

Download

(unavailable)

Abstract

Geometric models enable semantic information about real-world objects to beextracted from images. Model fitting algorithms need to find the best matchbetween a parameterized model and a given image. This task inherently requiresan objective function to estimate the error between a model parameterization andan image. The accuracy of this function directly influences the accuracy of theentire process of model fitting. Unfortunately, constructing these functions isa non-trivial task.Dedicated to the application of face model fitting, this paper proposes toconsider a multi-band image representation that indicates the facial components,from which a large set of image features is computed. Since it is not possibleto manually formulate an objective function that considers this large amount offeatures, we apply a Machine Learning framework to construct them. Thisautomatic approach is capable of considering the large amount of featuresprovided and yield highly accurate objective functions for face model fitting.Since the Machine Learning framework rejects non-relevant image features, weobtain high performance runtime characteristics as well.

BibTeX Entry

@InProceedings{wimmer08face,
  author =            {Matthias Wimmer and Christoph Mayer and Freek Stulp and Bernd Radig},
  title =             {Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components},
  booktitle =         {Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA), held in conjunction with CVPR},
  note =              {Non-archival.},
  bib2html_pubtype =  {Refereed Workshop Paper},
  bib2html_rescat =   {Image Understanding - Face Model Fitting},
  year =              {2008},
  abstract =          {  
Geometric models enable semantic information about real-world objects to be
extracted from images. Model fitting algorithms need to find the best match
between a parameterized model and a given image. This task inherently requires
an objective function to estimate the error between a model parameterization and
an image. The accuracy of this function directly influences the accuracy of the
entire process of model fitting. Unfortunately, constructing these functions is
a non-trivial task.
Dedicated to the application of face model fitting, this paper proposes to
consider a multi-band image representation that indicates the facial components,
from which a large set of image features is computed. Since it is not possible
to manually formulate an objective function that considers this large amount of
features, we apply a Machine Learning framework to construct them. This
automatic approach is capable of considering the large amount of features
provided and yield highly accurate objective functions for face model fitting.
Since the Machine Learning framework rejects non-relevant image features, we
obtain high performance runtime characteristics as well.
  }
}

Generated by bib2html.pl (written by Patrick Riley ) on Fri Jul 11, 2008 22:06:34 UTC


Computer Science IX | Technische Universität München