An Advanced Facial Expression Detection using Deep Neural Network

Abstract

Face serves as the primary source of contact for humans while interacting with each other. Facial Expressions fall under the bucket of non-verbal type of communication and plays a vital role in understanding the emotional state of a person. Identifying emotions through Facial Expressions can be used in various fields like revealing the Behavior of a candidate in a Job Interview, Understanding the comprehension level of the candidates in a classroom, Healthcare, Electoral campaign etc.; In additions to images fed to the Neural Network, Open Face tool is also used to extract the Facial Action Units of the subject in the dataset which contributes in training a neural network. We have designed and built a model-based technique with a high accuracy to classify the Facial based emotions. The data is trained on a Temporal Relations based Neural Network. Emotions can help us make decisions and it has a wide use case.