Using Kinect for real-time emotion recognition via facial expressions
Emotion recognition via facial expressions (ERFE) has attracted a great deal of interest with recent advances in artificial intelligence and pattern recognition. Most studies are based on 2D images, and their performance is usually computationally expensive. In this paper, we propose a real-time emotion recognition approach based on both 2D and 3D facial expression features captured by Kinect sensors. To capture the deformation of the 3D mesh during facial expression, we combine the features of animation units (AUs) and feature point positions (FPPs) tracked by Kinect. A fusion algorithm based on improved emotional profiles (IEPs) and maximum confidence is proposed to recognize emotions with these real-time facial expression features. Experiments on both an emotion dataset and a real-time video show the superior performance of our method.
Key wordsKinect, Emotion recognition Facial expression Real-time classification Fusion algorithm Support vector machine (SVM)
Unable to display preview. Download preview PDF.
- Ahlberg, J., 2001. Candide-3—an Updated Parameterised Face. Technical Report.Google Scholar
- Breidt, M., Biilthoff, H.H., Curio, C., 2011. Robust semantic analysis by synthesis of 3D facial motion. Proc. IEEE Int. Conf. on Automatic Face & Gesture Recognition and Workshops, p.713–719. [doi:10.1109/FG.2011.5771336]Google Scholar
- Chang, C.C., Lin, C.J., 2011a. LIBSVM: a Library for Support Vector Machines. Available from http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html.Google Scholar
- Cosker, D., Krumhuber, E., Hilton, A., 2011. A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling. Proc. IEEE Int. Conf. on Computer Vision, p.2296–2303. [doi:10.1109/ICCV.2011.6126510]Google Scholar
- Ekman, P., Friesen, W.V., 1978. Facial action coding system: a technique for the measurement of facial movement. Palo Alto.Google Scholar
- Hg, R.I., Jasek, P., Rofidal, C., et al., 2012. An RGB-D database using Microsoft’s Kinect for windows for face detection. Proc. 8th Int. Conf. on Signal Image Technology and Internet Based Systems, p.42–46. [doi:10. 1109/SITIS.2012.17]Google Scholar
- Li, B.Y., Mian, A.S., Liu, W.Q., et al., 2013. Using Kinect for face recognition under varying poses, expressions, illumination and disguise. Proc. IEEE Workshop on Applications of Computer Vision, p.186–192. [doi:10.1109/WACV.2013.6475017]Google Scholar
- Li, D.X., Sun, C., Hu, F.Q., et al., 2013. Real-time performance-driven facial animation with 3ds Max and Kinect. Proc. 3rd Int. Conf. on Consumer Electronics, Communications and Networks, p.473–476. [doi:10. 1109/CECNet.2013.6703372]Google Scholar
- Seddik, B., Maamatou, H., Gazzah, S., et al., 2013. Unsupervised facial expressions recognition and avatar reconstruction from Kinect. Proc. 10th Int. Multi-conf. on Systems, Signals & Devices, p.1–6. [doi:10.1109/SSD.2013.6564032]Google Scholar
- Stratou, G., Ghosh, A., Debevec, P., et al., 2011. Effect of illumination on automatic expression recognition: a novel 3D relightable facial database. Proc. IEEE Int. Conf. on Automatic Face & Gesture Recognition and Workshops, p.611–618. [doi:10.1109/FG.2011.5771467]Google Scholar
- van den Hurk, Y., 2012. Gender Classification with Visual and Depth Images. MS Thesis, Tilburg University, the Netherlands.Google Scholar
- Zhu, X.X., Ramanan, D., 2012. Face detection, pose estimation, and landmark localization in the wild. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.2879–2886. [doi:10.1109/CVPR.2012.6248014]Google Scholar