DocumentCode :
2188944
Title :
Are subtle expressions too sparse to recognize?
Author :
Le Ngo, Anh Cat ; Liong, Sze-Teng ; See, John ; Phan, Raphael Chung-Wei
Author_Institution :
Multimedia University Malaysia (MMU), Cyberjaya Campus, Jalan Multimedia 63100 Selangor Malaysia
fYear :
2015
fDate :
21-24 July 2015
Firstpage :
1246
Lastpage :
1250
Abstract :
As subtle emotions are slightly and involuntarily expressed, they need to be recorded by high-speed camera. Though this high frame-per-second rate allows better capture of subtle expressions, it typically generates a lot of redundant frames with rapid varying illumination and noise but without significant motions. The redundancy is analyzed and eliminated by Sparsity-Promoting Dynamic Mode Decomposition (DMDSP), which helps synthesize dynamically condensed sequences. Moreover, DMDSP can also visualize dynamics of subtle expressions in both temporal and spectral domains. As meaningful subtle expressions are temporarily sparse, DMDSP would be able to extract these meaningful dynamics and improve recognition rates of subtle expressions. The hypothesis is evaluated on CASME II, a database of spontaneous subtle facial expressions. Recognition performance measured by F1-score, recall and precision metrics showed a significant leap of improvement when DMDSP is used to preserve a small percentage of meaningful frames in sequences with temporally high sparsity levels.
Keywords :
Accuracy; Databases; Dynamics; Emotion recognition; Spectral analysis; Support vector machines; Videos; CASME II; Dynamic mode decomposition; Micro-expressions; Subtle emotion recognition; Temporal sparsity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Signal Processing (DSP), 2015 IEEE International Conference on
Conference_Location :
Singapore, Singapore
Type :
conf
DOI :
10.1109/ICDSP.2015.7252080
Filename :
7252080
Link To Document :
بازگشت