ABSTRACT
Facial emotions play an important role in understanding the intentions of human beings. To improve Human–Computer Interaction (HCI) and make it more natural, machines must be provided with the capability to understand the surrounding environment, focusing, in particular, on this aspect of human behavior. In this chapter, a Convolutional Neural Network (CNN) model for Facial Expression Recognition has been proposed. The CNN model has been trained using images of seven basic human emotions: happy, sad, angry, neutral, surprise, disgust and fear. The aim of this chapter is to classify each image into one of the seven facial emotion categories. This model has been validated using the FER2013 dataset provided by Kaggle to train, test and works in series, and the last layer of perceptron adjusts the weights and exponent values with each iteration. Furthermore, a novel background removal procedure applied to avoid dealing with multiple problems that may occur due to the position of the camera.
