TY - GEN
T1 - Facial Expression Classification with Deep Learning: A Comparative Study
AU - Cheah, Tuck Feng
AU - Lee, Chin Poo
AU - Lim, Kian Ming
AU - Lim, Jit Yan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Facial expression recognition is a significant area of research in computer vision with diverse applications. One of its primary challenges lies in the variations of facial expressions among individuals, cultures, and contexts. Various techniques, such as Convolutional Neural Networks and Vision Transformers, have emerged to address this challenge. This paper aims to compare the performance of five state-of-the-art models: VGG-19, EfficientNet-B7, Vision Transformer, Data-efficient Image Transformers, and Co-scale conv-attentional image Transformers, on two facial expression datasets: FER+ and CK+. The paper also provides an analysis in terms of strengths, weaknesses, and the factors affecting the performance.
AB - Facial expression recognition is a significant area of research in computer vision with diverse applications. One of its primary challenges lies in the variations of facial expressions among individuals, cultures, and contexts. Various techniques, such as Convolutional Neural Networks and Vision Transformers, have emerged to address this challenge. This paper aims to compare the performance of five state-of-the-art models: VGG-19, EfficientNet-B7, Vision Transformer, Data-efficient Image Transformers, and Co-scale conv-attentional image Transformers, on two facial expression datasets: FER+ and CK+. The paper also provides an analysis in terms of strengths, weaknesses, and the factors affecting the performance.
KW - CNN
KW - Convolution Neural Network
KW - Facial Expression
KW - Facial Expression Recognition
KW - Vision Transformer
UR - http://www.scopus.com/inward/record.url?scp=85186688982&partnerID=8YFLogxK
U2 - 10.1109/ICSPC59664.2023.10420210
DO - 10.1109/ICSPC59664.2023.10420210
M3 - Conference Proceeding
AN - SCOPUS:85186688982
T3 - 2023 IEEE 11th Conference on Systems, Process and Control, ICSPC 2023 - Proceedings
SP - 56
EP - 59
BT - 2023 IEEE 11th Conference on Systems, Process and Control, ICSPC 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th IEEE Conference on Systems, Process and Control, ICSPC 2023
Y2 - 16 December 2023
ER -