Emotion Recognition Model Based on Facial Expressions,Ethnicity and Gender Using Backpropagation Neural Network

摘要

Many emotion recognition approaches are built using facial expressions, but few of them use both the ethnicity and gender as attributes. The authors have developed an approach based on Artificial Neural Networks (ANN) using backpropagation algorithm to recognize the human emotion throughfacial expressions, ethnicity andgender. Their approach has been tested by using MSDEFdataset, and found that there is a positive effect on the accuracy of the recognition of emotion if they use both the ethnic group and gender as inputs to the system. Although this effect is not significant, but considerable (Improvement rate reached 8%). The authors also found that females have more accurate emotion expression recognition than males and found that the gender increases the accuracy of emotion recognition. Regardless of the used dataset, the authors 'approach obtained better results than some research on emotion recognition. This could be due to various reasons such as the type of the selected features and consideration of race and gender.