Human Emotion Recognition System Using Deep Learning Technique

Abstract

Now a day’s automatic emotion recognition system plays a vital role to recognize the human expressions. There are numerous applications
available ranging from surveillance cameras to detect the emotions. Emotion recognition is an important task in emotion detection deep
learning techniques are used for facial recognition. Images are used as input, and facial expressions are produced as output, such as happy,
sad, disgusted, angry, fearful, surprised, and neutral. In this paper, we design a deep Convolutional Neural Network (DCNN) model. This
model can be classifies seven various human facial emotions. This DCNN model is trained and tested using the FER (Facial Expression
Recognition) Data set. The deep FER is analysing the methods are very difficulties. The dataset used for experimentation is FER challenge
dataset available in KAGGLE repository. The implementation environment includes keras, tensorflow, and Open cv2 python packages. The
results include the comparison of accuracy of emotion detection between training and testing phase. The average accuracy achieved was
86.05%.