Visual Emotion Recognition Using Deep Neural Networks
Visual Emotion Recognition Using Deep Neural Networks
Author(s): Alexander I. Iliev, Ameya MoteSubject(s): Library and Information Science, Information Architecture, Library operations and management, Electronic information storage and retrieval, Other
Published by: Институт по математика и информатика - Българска академия на науките
Keywords: Emotion Recognition; Image Analysis; Language Understanding; Deep Con-volutional Neural Networks; Cross-Cultural Comparison
Summary/Abstract: 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 preexisting 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%.
Journal: Digital Presentation and Preservation of Cultural and Scientific Heritage
- Issue Year: 2022
- Issue No: XII
- Page Range: 77-88
- Page Count: 12
- Language: English