DocumentCode :
2218237
Title :
De-noised Event Related Potentials in facial Emotion recognition
Author :
Blaisie, Kampire ; Lasheng, Yu
Author_Institution :
Dept. of Comput. Sci., Central South Univ., Changsha, China
Volume :
5
fYear :
2010
fDate :
20-22 Aug. 2010
Abstract :
The key point in the de-noising of Event-Related Potentials (ERP) is to give a clear visualization of ERP between different trials representing different types of emotions (Anger, Surprise, Fear, Sadness, Happiness, Neutral).We used 6 pictures representing each emotion as a stimulus to a male actor and recorded a total of 60ERP trials 10 for each emotion. A Mexican hat wavelet was used to de-noise recorded ERPs. A better estimation of both amplitude and latency was achieved, together with a clear variation between noise free trials thus an easy way to Emotion recognition.
Keywords :
emotion recognition; face recognition; image denoising; image representation; wavelet transforms; ERP; Mexican hat wavelet; amplitude; de-noised event related potentials; facial emotion recognition; latency; male actor; noise free trials; picture representation; visualization; Complexity theory; Emotion Recognition; Event-Related Potentials; Noise; Wavelets; component;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Computer Theory and Engineering (ICACTE), 2010 3rd International Conference on
Conference_Location :
Chengdu
ISSN :
2154-7491
Print_ISBN :
978-1-4244-6539-2
Type :
conf
DOI :
10.1109/ICACTE.2010.5579137
Filename :
5579137
Link To Document :
بازگشت