Detection and Recognition of Human Emotion using Machine Learning

Abstract

This paper describes an emotion detection system based on real-time detection using image processing with human-friendly machine interaction. Facial detection has been around for decades. Taking a step ahead, human expressions displayed by face and felt by the brain, captured via video, electric signal, or image form can be approximated. To recognize emotions via images or videos is a difficult task for the human eye and challenging for machines thus detection of emotion by a machine requires many image processing techniques for feature extraction. This paper proposes a system that has two main processes such as face detection and facial expression recognition (FER). This research focuses on an experimental study on identifying facial emotions. The flow for an emotion detection system includes the image acquisition, preprocessing of an image, face detection, feature extraction, and classification. To identify such emotions, the emotion detection system uses KNN Classifier for image classification, and Haar cascade algorithm an Object Detection Algorithm to identify faces in an image or a real-time video. This system works by taking live images from the webcam. The objective of this research is to produce an automatic facial emotion detection system to identify different emotions based on these experiments the system could identify several people that are sad, surprised, and happy, in fear, are angry, etc.