Abstract

In this paper, we intended to test the hypothesis that there is a common denominator in complex emotions which human experts can identify, specifically in determining target scenarios. The underlining concept behind our work is that the system aims to compose complex emotions from simplex emotions. Our propose does not completely ignore the need for human operators since they (the human operators) make the final decision to confirm that the input video sequence corresponds to the simplex and complex emotion. However, the proposed system is designed in such a way that, theoretically once it is fully installed and operational, it would work on its own by automatically generating message alerts for the human operator. This entire process is based on the identification and labelling of what we call elementary or basic activities, namely events that are recognizable by artificial vision algorithms in this case HER. To test our hypothesis, we carried out an experiment on human emotions in Alzheimer’s interviews video. The results of experimentation showing that is possible identify complex emotions in video, include in important context how Alzheimer.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call