Fast Active Appearance Model Search Using Canonical Correlation Analysis

Rene Donner, Michael Reiter, Georg Langs, Philipp Peloschek, Horst BischofIEEE TPAMI 2006 · DOI · OpenReview

Abstract

A fast AAM search algorithm based on canonical correlation analysis (CCA-AAM) is introduced. It efficiently models the dependency between texture residuals and model parameters during search. Experiments show that CCA-AAMs, while requiring similar implementation effort, consistently outperform standard search with regard to convergence speed by a factor of four.
BibTeX
@article{donner2006fast,
  author = {Rene Donner and Michael Reiter and Georg Langs and Philipp Peloschek and Horst Bischof},
  title = {{Fast Active Appearance Model Search Using Canonical Correlation Analysis}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2006},
  doi = {10.1109/tpami.2006.206},
}

Loading related content...

Figure