Human Emotion Recognition from Facial Thermal Image using Histogram based Features and Multi-Class Support Vector Machine
A. Basu, Aurobinda Routray, Alok Kanti Deb · 2015
Emotions are one's subjective experiences which are associated with feelings, moods, affective and cognitive states.Human emotions generate unique signals which create unique patterns of sensation in our body.This paper reports a non-contact methodology to classify human emotions through thermal images of face.Histogram features obtained from facial patches are considered as the signature features and fed to a multi-class support vector machine for classification of the emotions.