Human emotion detection based on facial expression using convolution neural network

Abstract

Deep learning is an achievement inside the field of computer vision. This paper deals with deep learning frameworks to see outward appearances that address human feelings. Face feelings are the impressions of the inner emotions of a human. The human expressions play an essential role in nonverbal communication. Our article deals with eight standard feelings happiness, angry, sadness, fearing, surprising, disgusting, contempt and neutral. various researches have been performed, in appearing sagacious computer vision which can see the human's tendency. The proposed work achieves improved performance model with fewer epochs. To implement this, efficient algorithms and techniques are used while generating the model. In the preprocessing methodology, Histogram equalization has been applied to the raw input images. Batch Normalization technique is used in the proposed model for better learning rate. CK+ dataset is used for training and testing the model. To test the model in real time harr feature-based cascade classifier is used for detecting the face. the model was trained on Google Colab with a GPU.