Title | ||
---|---|---|
Manifold Analysis for Subject Independent Dynamic Emotion Recognition in Video Sequences |
Abstract | ||
---|---|---|
This paper proposes subject independent manifold features for dynamic emotion recognition. Facial action features, based on FACs, are firstly embedded into a low-dimensional manifold space using the ISOMAP algorithm, then the manifold features from different subjects are aligned into a global coordinate space by the supervised ISOMAP algorithm for recognition. To validate and evaluate the proposed manifold representation for emotion recognition, experiments with GMMs are presented. Given a new expression sequence, and tracked facial features, we are able to pin-point the actual occurrence of specific expressions, while characterizing its intensity by considering different expression temporal transition characteristics. Finally, experimental results show that our approach is able to separate different expressions successfully. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICIG.2009.76 | ICIG |
Keywords | Field | DocType |
facial action feature,video signal processing,manifold,expression temporal transition characteristic,gmm,face recognition,video sequences,subject independent dynamic emotion recognition,proposed manifold representation,subject independent manifold feature,low-dimensional manifold space,different expression,manifold feature,emotion recognition,isomap algorithm,image sequences,gaussian processes,manifold analysis,dynamic emotion recognition,different subject,subject independent dynamic emotion,gaussian mixture model,psychology,face,databases,feature extraction,manifolds | Facial recognition system,Computer vision,Pattern recognition,Expression (mathematics),Computer science,Coordinate space,Feature extraction,Manifold alignment,Artificial intelligence,Gaussian process,Manifold,Mixture model | Conference |
ISBN | Citations | PageRank |
978-1-4244-5237-8 | 0 | 0.34 |
References | Authors | |
9 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fan Ping | 1 | 23 | 2.54 |
Jiang Dongmei | 2 | 115 | 15.28 |
Wang Fengna | 3 | 0 | 0.34 |
Ravyse Ilse | 4 | 43 | 6.24 |
Hichem Sahli | 5 | 475 | 65.19 |