A Comparative Study of Performance of Facial Expression Recognition using Deep face and VGG16 Techniques

Abstract

Face recognition has advanced significantly over the past five years thanks to a variety of systems that propose cutting-edge methods that are largely supported by Deep Convolutional Neural Networks (DCNN). Face recognition is still an open problem in unconstrained situations, as shown by the recently released datasets, even though deep learning's performance on traditional datasets skyrocketed, giving the impression that this technique reached human performance.
The research on facial expression recognition and identification utilising the Deepface technique and VGG16 is discussed in this paper. Emotion recognition is a challenging and active research area. It is the process of identifying and categorizing human emotions based on the input data such as facial expressions, speech, text, or physiology. Machine learning models are used in emotion recognition to learn complex patterns and features from the input data. Emotion recognition for human mood analysis is a multidisciplinary field that involves utilizing various technologies to understand and interpret an individual's emotional state In comparison to the existing method found in the literature, the suggested method yields superior results. Universal emotions are Happy, Sad, Fear, Angry, Surprise and Disgust. Based on the Human mood work allocation can be done to the employee. To find the Human mood using the Face recognition technique is the method used in this paper.