Genetic Model Optimization for Hausdorff Distance-Based Face Localization

Abstract

In our previous work we presented a model-based approach to perform robust, high-speed face localization based on the Hausdorff distance. A crucial step during the design of the system is the choice of an appropriate edge model that fits for a wide range of different human faces. In this paper we present an optimization approach that creates and successively improves such a model by means of genetic algorithms. To speed up the process and to prevent early saturation we use a special bootstrapping method on the sample set. Several initialization functions are tested and compared.

Cite

Text

Kirchberg et al. "Genetic Model Optimization for Hausdorff Distance-Based Face Localization." European Conference on Computer Vision, 2002. doi:10.1007/3-540-47917-1_11

Markdown

[Kirchberg et al. "Genetic Model Optimization for Hausdorff Distance-Based Face Localization." European Conference on Computer Vision, 2002.](https://mlanthology.org/eccv/2002/kirchberg2002eccv-genetic/) doi:10.1007/3-540-47917-1_11

BibTeX

@inproceedings{kirchberg2002eccv-genetic,
  title     = {{Genetic Model Optimization for Hausdorff Distance-Based Face Localization}},
  author    = {Kirchberg, Klaus J. and Jesorsky, Oliver and Frischholz, Robert},
  booktitle = {European Conference on Computer Vision},
  year      = {2002},
  pages     = {103-111},
  doi       = {10.1007/3-540-47917-1_11},
  url       = {https://mlanthology.org/eccv/2002/kirchberg2002eccv-genetic/}
}