Paper Title
Real-Time Recognition of Human Facial Expressive Behavior using Deep Convnet Model

Humans display their emotional states through facial expressions, which depend on many factors: the physical characteristics of the face; the neurological wiring of the brain; social conventions that signal what emotions are appropriate settings; and one's current mood. Recent research suggests that humans may have facial expressions not only for communicating with other humans but also to coordinate their actions with other members of their species. In robotics, analyses of human emotions can help in training bots to make the best decisions. Real-time face recognition targets match human faces in digital images or video sequences/frames against the faces in a database. This work proposes a novel architecture to efficiently detect human expressive behavior utilizing a deep convolution neural network (ConvNET), trained on the FER 2013 dataset, for real-time detection, facial features are extracted by utilizing the Haar cascade classifier. The proposed model achieved accuracy of 78 percent. This paper provides a thorough examination of the various methodologies used for emotion recognition and conducts an empirical analysis of the proposed model with previous works. Keywords - Face recognition, Emotion recognition, Haar cascade, Deep ConvNET, Real-time detection, Open CV.