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, Freek Stulp, and Bernd Radig. Enabling Users to Guide the Design of Robust Model FittingAlgorithms. In Interactive Computer Vision Workshop, held in conjunction with the Eleventh IEEE International Conference on Computer Vision (ICCV), 2007. Non-archival.

Download

[PDF]3.2MB  

Abstract

Model-based image interpretation extracts high-level information from imagesusing a priori knowledge about the object of interest. The computationalchallenge in model fitting is to determine the model parameters that best matcha given image, which corresponds to finding the global optimum of the objectivefunction. When it comes to the robustness and accuracy of fitting models to specificimages, humans still outperform state-of-the-art model fitting systems. For thisreason, we propose a method in which non-experts can guide the process ofdesigning model fitting algorithms. In particular, this paper demonstrates howto obtain robust objective functions for face model fitting applications, bylearning their calculation rules from example images annotated by humans. Weevaluate the obtained function using a publicly available image database andcompare it to a recent state-of-the-art approach in terms of accuracy.

BibTeX Entry

@InProceedings{wimmer07enabling,
  author =            {Matthias Wimmer and Freek Stulp and Bernd Radig},
  title =             {Enabling Users to Guide the Design of Robust Model Fitting
Algorithms},
  booktitle =         {Interactive Computer Vision Workshop, held in conjunction with the Eleventh IEEE International Conference on Computer Vision (ICCV)},
  note =              {Non-archival.},
  bib2html_pubtype =  {Refereed Workshop Paper},
  bib2html_rescat =   {Image Understanding - Face Model Fitting},
  year =              {2007}
  abstract =          {
  Model-based image interpretation extracts high-level information from images
using a priori knowledge about the object of interest. The computational
challenge in model fitting is to determine the model parameters that best match
a given image, which corresponds to finding the global optimum of the objective
function. 
When it comes to the robustness and accuracy of fitting models to specific
images, humans still outperform state-of-the-art model fitting systems. For this
reason, we propose a method in which non-experts can guide the process of
designing model fitting algorithms. In particular, this paper demonstrates how
to obtain robust objective functions for face model fitting applications, by
learning their calculation rules from example images annotated by humans. We
evaluate the obtained function using a publicly available image database and
compare it to a recent state-of-the-art approach in terms of accuracy.  
  }
}

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


Computer Science IX | Technische Universität München