Application of Convolutional Neural Networks for the Classification of Human Emotions
Application of Convolutional Neural Networks for the Classification of Human Emotions
Autori:
Izdanje: Sinteza 2023 - International Scientific Conference on Information Technology and Data Related Research
DOI: 10.15308/Sinteza-2023-52-59
Oblast: Computer Science and Artificial Intelligence
Stranice: 52-59
Apstrakt:
Computer vision training is implemented using deep learning. Deep learning can be applied to solve a variety of classification problems. Accordingly, the problem of recognizing human emotions based on facial images can be singled out. For this problem, the use of convolutional neural networks proved to be the best solution. Specifically, the convolutional neural network models used in this paper are ResNet50, VGG16, and VGG19. The CNN model was implemented using the Keras library and the Python programming language. As input to these models, the RAF-DB database containing images of human faces with emotions was used. Based on the results obtained from the mentioned three CNN models, VGG16 proved to be the best, achieving a precision of 83.61%. VGG19 was on the second place with an accuracy of 82.37%, and the worst was ResNet50, whose accuracy was 75.31%.
Ključne reči: Convolutional Neural Networks, classification problems, RAF-DB, CNN models
Priložene datoteke:
- US - SINTEZA - 2023 - RAD 8 - 52-59 ( veličina: 777,28 KB, broj pregleda: 118 )
Kategorije objave:
Radovi na konferenciji Sinteza 2023, Beograd, Srbija
Zahvaljujemo se što ste preuzeli publikaciju sa portala Singipedia.
Ukoliko želite da se prijavite za obaveštenja o sadržajima iz oblasti ove publikacije, možete nam ostaviti adresu svoje elektronske pošte.
Preuzimanje citata:
BibTeX format
RefWorks Tagged format
Unapred formatirani prikaz citata
BibTeX format
@article{article, author = {N. Matijašević, A. Samčović and M. Đogatović}, title = {Application of Convolutional Neural Networks for the Classification of Human Emotions}, journal = {Sinteza 2023 - International Scientific Conference on Information Technology and Data Related Research}, year = 2023, pages = {52-59}, doi = {10.15308/Sinteza-2023-52-59} }
RT Conference Proceedings A1 Nikola Matijašević A1 Andreja Samčović A1 Marko Đogatović T1 Application of Convolutional Neural Networks for the Classification of Human Emotions AD Univerzitet Singidunum, Beograd, Beograd, Srbija YR 2023 NO doi: 10.15308/Sinteza-2023-52-59
N. Matijašević, A. Samčović and M. Đogatović, Application of Convolutional Neural Networks for the Classification of Human Emotions, Univerzitet Singidunum, Beograd, 2023, doi:10.15308/Sinteza-2023-52-59