Regression-Based Multi-view Facial Expression Recognition

Ognjen Rudovic, Ioannis Patras, Maja Pantic

Abstract

We present a regression-based scheme for multi-view facial expression recognition based on 2D geometric features. We address the problem by mapping facial points (e.g. mouth corners) from non-frontal to frontal view where further recognition of the expressions can be performed using a state-of-the-art facial expression recognition method. To learn the mapping functions we investigate four regression models: Linear Regression (LR), Support Vector Regression (SVR), Relevance Vector Regression (RVR) and Gaussian Process Regression (GPR). Our extensive experiments on the CMU Multi-PIE facial expression database show that the proposed scheme outperforms view-specific classifiers by utilizing considerably less training data.
BibTeX
@inproceedings{rudovic2010regression,
  author = {Ognjen Rudovic and Ioannis Patras and Maja Pantic},
  title = {{Regression-Based Multi-view Facial Expression Recognition}},
  booktitle = {ICPR},
  year = {2010},
  doi = {10.1109/icpr.2010.1001},
}

Loading related content...

Figure