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
         
        
        
        
        
            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;
         
        
        
        
            Conference_Titel : 
Advanced Computer Theory and Engineering (ICACTE), 2010 3rd International Conference on
         
        
            Conference_Location : 
Chengdu
         
        
        
            Print_ISBN : 
978-1-4244-6539-2
         
        
        
            DOI : 
10.1109/ICACTE.2010.5579137