An Intelligent System Design for Emotion Recognition and Rectification Using Machine Learning

Abstract

Nonverbal cues that are sent through facial expressions are crucial in interpersonal interactions. Automatic facial expression recognition can be a crucial component of typical human-machine interfaces. A facial expression can be viewed from the perspective of automatic recognition as consisting of changes to the facial components' spatial relationships, changes in the pigmentation of the face, or both. The CVIP tools help us achieve our goals. We used a train data set of six facial expressions from three different people. For the train data set, we used a total of 90 border mask samples, and for the test data set, we used 30 border mask samples.