Análise de Desempenho e Efetividade de Redes Neurais Convolucionais em Plataformas de GPU e CPU Aplicadas ao Reconhecimento de Emoções Através de Expressões Faciais em Seres Humanos
Abstract
Considering the growing interest in the field of human-computer interaction and that this iteration has become something more and more natural and social, together with the increase in the computational capacity provided by GPUs and CPUs, areas such as emotion recognition have been shown to be of great importance and relevance for the scientific community. However, even with several works done, detecting and recognizing emotions computationally and with the same ease that humans recognize is still a relevant problem to be explored. To this end, seeking to explore this theme, this work adopted the use of Convolutional Artificial Neural Networks (ANN) in the recognition of emotions in humans from facial expressions. The results showed that, with the training of an ANN in GPUs, it was possible to reduce the computational time by up to 89% and increase the accuracy to 65%.References
Amin, D., Chase, P., and Sinha, K. (2017). Touchy feely: An emotion recognition challenge. Palo alto: Stanford.
Bartlett, M. S., Littlewort, G., Fasel, I., and Movellan, J. R. (2003). Real time face detection and facial expression recognition: development and applications to human computer interaction. In 2003 Conference on computer vision and pattern recognition workshop, volume 5, pages 53–53. IEEE.
Ekman, P. (1973). Cross-cultural studies of facial expression. Darwin and facial expression: A century of research in review, 169222(1).
Leão, L. P., Bezerra, J. S., Matos, L. N., and Nunes, M. A. S. N. (2012). Detecção de expressões faciais: uma abordagem baseada em análise do uxo óptico. Revista GEINTEC-Gestão, Inovação e Tecnologias, 2(5):472–489.
Tang, H. and Huang, T. S. (2008). 3d facial expression recognition based on properties of line segments connecting facial feature points. In 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition, pages 1–6. IEEE.
Vargas, A. C. G., Paes, A., and Vasconcelos, C. N. (2016). Um estudo sobre redes neurais con- volucionais e sua aplicação em detecção de pedestres. In Proceedings of the xxix conference on graphics, patterns and images, volume 1.
Bartlett, M. S., Littlewort, G., Fasel, I., and Movellan, J. R. (2003). Real time face detection and facial expression recognition: development and applications to human computer interaction. In 2003 Conference on computer vision and pattern recognition workshop, volume 5, pages 53–53. IEEE.
Ekman, P. (1973). Cross-cultural studies of facial expression. Darwin and facial expression: A century of research in review, 169222(1).
Leão, L. P., Bezerra, J. S., Matos, L. N., and Nunes, M. A. S. N. (2012). Detecção de expressões faciais: uma abordagem baseada em análise do uxo óptico. Revista GEINTEC-Gestão, Inovação e Tecnologias, 2(5):472–489.
Tang, H. and Huang, T. S. (2008). 3d facial expression recognition based on properties of line segments connecting facial feature points. In 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition, pages 1–6. IEEE.
Vargas, A. C. G., Paes, A., and Vasconcelos, C. N. (2016). Um estudo sobre redes neurais con- volucionais e sua aplicação em detecção de pedestres. In Proceedings of the xxix conference on graphics, patterns and images, volume 1.
Published
2020-10-21
How to Cite
HECK, Leandro; KÜNAS, Cristiano; PADOIN, Edson.
Análise de Desempenho e Efetividade de Redes Neurais Convolucionais em Plataformas de GPU e CPU Aplicadas ao Reconhecimento de Emoções Através de Expressões Faciais em Seres Humanos. In: UNDERGRADUATE RESEARCH WORKSHOP - SYMPOSIUM ON HIGH PERFORMANCE COMPUTING SYSTEMS (SSCAD), 21. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 8-13.
DOI: https://doi.org/10.5753/wscad_estendido.2020.14083.
