Real-Time Intelligent Facial Expression Recognition System

Facial expression plays an important role in conveying the non-verbal cues of any person. Recognizing the facial expression is reffered to as the identification of emotional state. In this research, a real-time detection of emotions has been performed by training the model into different data sets and then emotional state of a person is displayed. The aim of the project is to recognize human emotions in real-time which are based on their facial expressions. Human sentiments play an important role in every one’s life which has increased the interaction between human and machine and has taken the focus of scientist to fill this gap between Human Machine Interaction (HMI). Tremendous work has been done in recognizing emotions using facial expression but little work is done on recognizing eight emotions in real-time. For this purpose, a real-time system to judge eight emotions using facial expression hsa been designed. Further, the performance of the proposed method is evaluated by using trained database using Convolution Neural Network (CNN) and Support vector machines (SVM). Experimental results and prototype show the accuracy of detected emotions in realtime. We contributed our part to recognize human emotions in Real-time and increased the accuracy for CNN algorithm. A comparative study has also been done in which SVM and CNN are compared for emotion recognition in real-time. The study is concluded which results in recognition of eight universal emotions; neutral, happy, sad, anger, disturbed, fear, surprised, nervous in real time by the proposed system.