A Machine Learning Model for Recognition and Classification of Emotion Using Facial Expressions

Emotion recognition has become a major area of multidisciplinary research in recent years and has many potential applications in the development of artificial intelligence and human-computer interface related design of human health detection. Expansion experiments are carried out by researchers using various stimuli, attributes, and categorization methods. This paper makes use of hybrid feature optimization algorithms i. e, IWSS Embedded and PSO for recognizing emotions using facial expressions. A pretrained model ResNet50V2 is used as a feature extractor and an image filter called Discretization is applied in order to improve the accuracy of the proposed approach. The results revealed that the methodology attained an overall accuracy of 75%.