Back to Search
Start Over
Magnifying Subtle Facial Motions for Effective 4D Expression Recognition
- Source :
- IEEE Transactions on Affective Computing, IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers, 2019, 10 (4), pp.524-536, IEEE Transactions on Affective Computing, 2019, 10 (4), pp.524-536
- Publication Year :
- 2021
- Publisher :
- arXiv, 2021.
-
Abstract
- In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed. It combines two growing but disparate ideas in Computer Vision -- computing the spatial facial deformations using tools from Riemannian geometry and magnifying them using temporal filtering. The flow of 3D faces is first analyzed to capture the spatial deformations based on the recently-developed Riemannian approach, where registration and comparison of neighboring 3D faces are led jointly. Then, the obtained temporal evolution of these deformations are fed into a magnification method in order to amplify the facial activities over the time. The latter, main contribution of this paper, allows revealing subtle (hidden) deformations which enhance the emotion classification performance. We evaluated our approach on BU-4DFE dataset, the state-of-art 94.18% average performance and an improvement that exceeds 10% in classification accuracy, after magnifying extracted geometric features (deformations), are achieved.<br />Comment: International Conference On Pattern Recognition 2016
- Subjects :
- FOS: Computer and information sciences
Computer science
Emotion classification
Computer Vision and Pattern Recognition (cs.CV)
Feature extraction
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Riemannian geometry
Facial recognition system
subtle motion magnification
symbols.namesake
Index Terms—4D Facial Expression Recognition
0202 electrical engineering, electronic engineering, information engineering
Computer vision
Hidden Markov model
key frame detection
ComputingMethodologies_COMPUTERGRAPHICS
Facial expression
business.industry
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
020207 software engineering
Spectral clustering
Human-Computer Interaction
Support vector machine
symbols
020201 artificial intelligence & image processing
Artificial intelligence
business
Software
Subjects
Details
- ISSN :
- 19493045
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Affective Computing, IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers, 2019, 10 (4), pp.524-536, IEEE Transactions on Affective Computing, 2019, 10 (4), pp.524-536
- Accession number :
- edsair.doi.dedup.....75f543d7b766f73f9fb3fc747421ffc8
- Full Text :
- https://doi.org/10.48550/arxiv.2105.02319