Recognition of Changes in Human Emotion from Face Image Sequence using Triangulation Induced Barycentre-Orthocentre Paired Distance Signature

Intelligent recognition of human emotion is an emerging field of affective computing that emphasizing the capability of a computer to understand the emotional state of humans. Gradual changes in human emotion can be displayed through understanding the nature of the transition of six basic facial expressions viz. anger(AN), disgust(DI), fear(FE), happiness(HA), sadness(SA), and surprise(SU). Here, we report a framework for the identification of transition from one emotional state to another as reflected in human faces and available in video sequences. we introduce the triangulation process to achieve the goal that uses salient landmark points extracted from video frames and produces a geometric feature describing the transition of basic emotion. For the classification of basic facial expressions, Multilayer Perceptron (MLP) uses a barycentre-orthocentre paired distance signature produced by the triangulation process. Our proposed approach shows impressive recognition results on different benchmark video datasets viz. Extended Cohn-Kanade Dataset (CK+), MMI, and MUG with average accuracy 97.55%, 92.07%, and 98.50% respectively.