4D facial expression recognition
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1594-1601
Abstract
In this paper, we focus on discrete expression classification using dynamic 3D sequences (4D data) recording the facial movements. A robust approach for registering 4D data is proposed and a variant of local binary patterns on three orthogonal planes is used for feature extraction. We present a fully automatic facial expression recognition pipeline. The system was evaluated on the publicly available facial expression database BU-4DFE and promising results were obtained.Keywords
This publication has 32 references indexed in Scilit:
- Expression recognition from 3D dynamic faces using robust spatio-temporal shape features2011
- Robust single-view geometry and motion reconstructionACM Transactions on Graphics, 2009
- A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous ExpressionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model ApproachIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Discrete conformal mappings via circle patternsACM Transactions on Graphics, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Generating Realistic Facial Expressions with Wrinkles for Model-Based CodingComputer Vision and Image Understanding, 2001
- Surface matching for object recognition in complex three-dimensional scenesImage and Vision Computing, 1998
- A Combined Corner and Edge Detector1988
- Theory of edge detectionProceedings of the Royal Society of London. B. Biological Sciences, 1980