Human emotional states modeling by Hidden Markov Model

This paper presents an attempt of using Hidden Markov Model to model the high level emotions (such as, encouraging, interest, unsure, disagreeing and discouraging) through low level facial expressions (such as, happy, sad, surprise and neutral). The rationale behind using HMM is that the HMM models human brain as human emotion is quite complex, naturally a human instinct contain hidden layer as well (like sub conscious mind). In addition, Markov state chain property is good to model human emotion as our emotion is also through our mind state that it is always dependent on our previous state of our emotion and current event will end up our current emotion state. Our proposed work is to develop an emotion indexer acting as a higher level analysis to interpret more advanced emotional states out of the basic emotions.