Recognize Human Emotions: Recognition from DCT
Published: 2010
Author(s) Name: S. B. Nimbekar, D. D. Badgujar
Locked
Subscribed
Available for All
Abstract
The ability to recognize emotion is one of the hallmarks of emotional intelligence, an aspect of human
intelligence that has been argued to be even more important than mathematical and verbal intelligence. This
paper proposes that machine intelligence needs to include emotional intelligence and demonstrate results toward
this goal: developing a machines ability to recognize human emotion from given facial parameter. We describe
difficult issues unique to obtain reliable affective data and collect a large set of data from a subject and
experience each of two emotional states. This paper presents techniniqus for feature extraction and use algorithm
for classification, which is on kernel based. We got 100% recognition accuracy on three classes of emotion, including neutral.
Keywords : DCT, Mean, Entropy, Energy, SVM.
View PDF