Coupled Gaussian processes for pose-invariant facial expression recognition

We propose a method for head-pose invariant facial expression recognition that is based on a set of characteristic facial points. To achieve head-pose invariance, we propose the Coupled Scaled Gaussian Process Regression (CSGPR) model for head-pose normalization. In this model, we first learn indepe...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 35(2013), 6 vom: 15. Juni, Seite 1357-69
1. Verfasser: Rudovic, Ognjen (VerfasserIn)
Weitere Verfasser: Pantic, Maja, Patras, Ioannis Yiannis
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2013
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM226801691
003 DE-627
005 20231224072235.0
007 cr uuu---uuuuu
008 231224s2013 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2012.233  |2 doi 
028 5 2 |a pubmed24n0756.xml 
035 |a (DE-627)NLM226801691 
035 |a (NLM)23599052 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Rudovic, Ognjen  |e verfasserin  |4 aut 
245 1 0 |a Coupled Gaussian processes for pose-invariant facial expression recognition 
264 1 |c 2013 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 15.11.2013 
500 |a Date Revised 19.04.2013 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a We propose a method for head-pose invariant facial expression recognition that is based on a set of characteristic facial points. To achieve head-pose invariance, we propose the Coupled Scaled Gaussian Process Regression (CSGPR) model for head-pose normalization. In this model, we first learn independently the mappings between the facial points in each pair of (discrete) nonfrontal poses and the frontal pose, and then perform their coupling in order to capture dependences between them. During inference, the outputs of the coupled functions from different poses are combined using a gating function, devised based on the head-pose estimation for the query points. The proposed model outperforms state-of-the-art regression-based approaches to head-pose normalization, 2D and 3D Point Distribution Models (PDMs), and Active Appearance Models (AAMs), especially in cases of unknown poses and imbalanced training data. To the best of our knowledge, the proposed method is the first one that is able to deal with expressive faces in the range from -45° to +45° pan rotation and -30° to +30° tilt rotation, and with continuous changes in head pose, despite the fact that training was conducted on a small set of discrete poses. We evaluate the proposed method on synthetic and real images depicting acted and spontaneously displayed facial expressions 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Pantic, Maja  |e verfasserin  |4 aut 
700 1 |a Patras, Ioannis Yiannis  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 35(2013), 6 vom: 15. Juni, Seite 1357-69  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:35  |g year:2013  |g number:6  |g day:15  |g month:06  |g pages:1357-69 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2012.233  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 35  |j 2013  |e 6  |b 15  |c 06  |h 1357-69