Survey on Upper Body Gesture with Facial Emotions Recognition

EasyChair Preprint no. 6907

Abstract

Real Time emotion recognition and Body Gesture has become a trending research topic. While works based on facialexpressions with upper body Gesture recognizing a less explored topic. We present a new comprehensivesurvey hoping to enhance research in the field. We first introduce upper bodyActivity as a component of what is commonly knownas "Human body language". We then Compare a completeframework for automatic emotional body gesture recognition. We also compare person detection andbodypose estimation methods both in 2D(RGB) and 3D. We then comment the recent literature related to representation learning and emotionrecognition from images of emotionally expressive gestures. We also discuss multi-modal approaches that combine facewith body gestures for improved emotion recognition. We then Analysis Existing Algorithm for Human Activity and Emotion’s and Compare Real Time Facial Emotion from Facial Expression Using Deep Learning with Genetic Algorithm.While pre-processing methodologies (e.g. human detection and pose estimation)are nowadays mature technologies fully developed for robust large scale analysis, we show that for emotion recognition the quantity oflabelled data is scarce

Keyphrases: AI Artificial Intelligence, CV Computer Vision, MI- Machine Learning

@Booklet{EasyChair:6907,
  author = {Ravi Shankar Sharma and Pratima Gautam},
  title = {Survey on Upper Body Gesture with Facial Emotions Recognition},
  howpublished = {EasyChair Preprint no. 6907},

  year = {EasyChair, 2021}}