Emotion Detection: Comparison of Various Techniques

Abstract

Expressions and body language can tell us  a lot about what people are thinking. They are a form of  non-verbal communication which tells us about how the  person is feeling. It describes the mood of the person like  whether he is happy or sad. This detection can be done  using various techniques which are already based in the  research papers like instrumented sensor technology and  computer vision. It means that the expressions can be  classified under different techniques like whether motion of  the person is still or he is moving. This paper focuses on  detecting the emotions of the person using computer vision.  Using the Artificial Intelligence Technique and Mediapipe along with Computer Vision we are focusing on various  joints in our body and storing their coordinates in a python  file created there and then testing our Algorithm to detect  the mood of the person. In addition, a dialogue box also  pops us while detecting the emotions which tells us about  the probability i.e the accuracy of our detection and also  tells us about which emotion it is. The current model  consists of three emotions, they are happy, sad and  victorious i.e Gestures are detected. The algorithm is  focusing on the difference between the coordinates and  detect the emotions. Detection at a distance might be an  issue as the coordinates will be different then. This paper is  a thorough general overview of Body Gesture Detection  with a brief description of things which are going to be  there.