AVALIAÇÃO DE RECONHECIMENTO DE EMOÇÃO DIMENSIONAL COM UMA ABORDAGEM BASEADA EM ATENÇÃO

Antonio José da Silva Ferreira; Gabriela Regina Soares; João Baptista Cardia Neto

doi:10.31510/infa.v19i2.1523

Authors

Antonio José da Silva Ferreira Faculdade de Tecnologia de Catanduva (Fatec) – Catanduva – SP – Brasil https://orcid.org/0000-0002-0202-8416
Gabriela Regina Soares Faculdade de Tecnologia de Catanduva (Fatec) – Catanduva – SP – Brasil https://orcid.org/0000-0002-1895-0026
João Baptista Cardia Neto Faculdade de Tecnologia de Catanduva (Fatec) – Catanduva – SP – Brasil https://orcid.org/0000-0002-2727-1383

DOI:

https://doi.org/10.31510/infa.v19i2.1523

Keywords:

valence, arousal, non-verbal feedback, convolutional neural networks

Abstract

Non-verbal feedback and the recognition of facial expressions have been an area of much research in the last decades. Facial expressions are a concrete way to recognize emotions and "teaching" computers to detect correctly what each facial expression means and to which emotion it is attached. Thus, in the scope of image recognition, Convolutional Neural Networks (CNN), through their layering over image pixels, facilitate pattern discovery. Therefore, through the application a CNN with an attention mechanism, the objective of this paper is to decode the non-verbal expressions present in the used database and identify to which emotion it is linked. Through the analysis of the CCC (Correlation Coefficient of Concordance) and the Mean Squared Error (RMSE) for the valence and arousal dimensions, this paper shows that the method used brings results, but there is still room for improvement in machine learning.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

AL TAWIL, R. Nonverbal Communication in Text-Based, Asynchronous Online Education. The International Review of Research in Open and Distributed Learning, v. 20, n. 1, 28 fev. 2019. DOI: https://doi.org/10.19173/irrodl.v20i1.3705

CRUZ, A. A. da. Uma abordagem para reconhecimento de emoção por expressão facial baseada em redes neurais de convolução. 2019. 120 f. Dissertação (Mestrado em Informática) – Universidade Federal do Amazonas, Manaus, 2019. Disponível em: <https://tede.ufam.edu.br/handle/tede/7320>. Acesso em: 04 abr. 2022.

EKMAN, P.; FRIESEN, W.V. Facial action coding system: a technique for the measurement of facial movement. Palo Alto, 1978. DOI: https://doi.org/10.1037/t27734-000

FREITAS-MAGALHÃES, A. O código de Ekman: o cérebro, a face e a emoção. Porto, Portugal: Editora Escrytos, 2018. 443 p.

GÉRON, A. Hands-on machine learning with scikit-learn and tensorflow: Concepts. Tools, and Techniques to build intelligent systems. Editora O’Reilly, 2017.

HAMOND, L.; HIMONIDES, E.; WELCH, G. A natureza do feedback no ensino e na aprendizagem de piano com o uso de tecnologia digital no ensino superior. Orfeu, Florianópolis, v. 6, n. 1, p. 01-31, 2021. DOI: https://doi.org/10.5965/2525530406012021e0011. Disponível em: <https://www.revistas.udesc.br/index.php/orfeu/article/view/19928>. Acesso em: 01 abr. 2022. DOI: https://doi.org/10.5965/2525530406012021e0011

HAYKIN, S. O. Neural networks: a comprehensive foundation. 2ª Edição. Editora Pearson Education, 1998. 842 p.

KATTENBORN, T. et al. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, v. 173, p. 24-49, 2021. DOI: https://doi.org/10.1016/j.isprsjprs.2020.12.010

LIU, C.; CALVO, R. A.; LIM, R. Improving medical students’ awareness of their non-verbal communication through automated non-verbal behavior feedback. Front. ICT, 2016. DOI: 10.3389/fict.2016.00011. Disponível em: <https://www.frontiersin.org/articles/10.3389/fict.2016.00011/full>. Acesso em: 01 abr. 2022.

MINAEE, S.; MINAEI, M.; ABDOLRASHIDI, A. Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network. Sensors (Basel). 2021. Disponível em: <https://paperswithcode.com/paper/deep-emotion-facial-expression-recognition>. Acesso em: 26 ago. 2022. DOI: https://doi.org/10.3390/s21093046

PAULISTA, G. da P. Incorporando meta learning: o papel crítico da expressão não-verbal na interação face a face e na performance de equipes de trabalho. 2009. Tese (Doutorado em Engenharia e Gestão do Conhecimento) – Universidade Federal de Santa Catarina, Florianópolis, 2009. Disponível em: <https://repositorio.ufsc.br/handle/123456789/103237>. Acesso em: 07 mar. 2022.

PEDRO, T. M. J. Alexitimia e avaliação da valência e arousal de expressões emocionais. 2013. Dissertação (Mestrado em Psicologia Clínica e da Saúde) – Universidade de Aveiro, 2013. Disponível em: < http://hdl.handle.net/10773/12764>. Acesso em: 04 abr. 2022.

RUSSEL, S.; NORVIG, P. Artificial Intelligence: a modern approach. 4ª Edição. Editora Pearson Education, 2021. 1115 p.

SKANSI, S. Introduction to Deep Learning: from logical calculus to artificial intelligence. Editora Springer, 2018. DOI: https://doi.org/10.1007/978-3-319-73004-2

SIQUEIRA, H.; MAGG, S.; WERMTER, S. (2020). Efficient Facial Feature Learning with Wide Ensemble-Based Convolutional Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. Disponível em: <https://paperswithcode.com/paper/frame-attention-networks-for-facial>. Acesso em: 28 ago. 2022. DOI: https://doi.org/10.1609/aaai.v34i04.6037

YU, et al. Customized expression recognition for performance-driven cutout character animation. Applications of Computer Vision (WACV), 2016, IEEE Winter Conference on, p. 1–9. DOI: https://doi.org/10.1109/WACV.2016.7477449

WEN, Z. et al. Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition. Disponível em: <https://arxiv.org/pdf/2109.07270v4.pdf>. Acesso em: 28 set. 2022.