Visual Emotion Recognition Using Deep Neural Networks

It has been proven historically how important feelings and expressions are. They form an important role in communications between individuals of different culture. In the present day, Globalization has led to exchange of vast number of ideas among people on Earth. This gives rise to a unique challenge of identifying what the person in front is speaking about and formulate opinions likewise. Failing to do that would often result in unfortunate consequences. This paper leads to make inroads in this field and provide a basis to other future researchers. We took images from a pre-existing video dataset and recognize the emotions behind it. Through a series of experiments, a final neural network model was created which gave an accuracy of 88%.

Abstract licence: CC BY-NC

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.