TY - GEN
T1 - 3D facial expression recognition using deep feature fusion CNN
AU - Tian, Kun
AU - Zeng, Liaoyuan
AU - McGrath, Sean
AU - Yin, Qian
AU - Wang, Wenyi
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - As an important way of human communication, facial expression not only reflects our mental activities but also provides useful information for human behavior research. Recently, 3D technology becomes promising method to achieve robust facial expression analysis. 3D face scans are robust to lighting and pose variations. In this paper, a novel deep feature fusion convolution neural network (CNN) is designed for 3D facial expression recognition (FER). Each 3D face scan is firstly represented as 2D facial attribute maps (including depth, normal, and shape index values). Then, we combine different of facial attribute maps to learn facial representations by fine-tuning a pre-trained deep feature fusion CNN subnet trained from a large-scale image dataset for universal visual tasks. Moreover, Global Average Pooling is utilized to reduce the number of parameters to decrease the effect of overfitting. The experiments are conducted on the Bosphorus database and the results demonstrate the effectiveness of the proposed method.
AB - As an important way of human communication, facial expression not only reflects our mental activities but also provides useful information for human behavior research. Recently, 3D technology becomes promising method to achieve robust facial expression analysis. 3D face scans are robust to lighting and pose variations. In this paper, a novel deep feature fusion convolution neural network (CNN) is designed for 3D facial expression recognition (FER). Each 3D face scan is firstly represented as 2D facial attribute maps (including depth, normal, and shape index values). Then, we combine different of facial attribute maps to learn facial representations by fine-tuning a pre-trained deep feature fusion CNN subnet trained from a large-scale image dataset for universal visual tasks. Moreover, Global Average Pooling is utilized to reduce the number of parameters to decrease the effect of overfitting. The experiments are conducted on the Bosphorus database and the results demonstrate the effectiveness of the proposed method.
KW - 3D facial expression recognition
KW - Deep feature fusion CNN
KW - Feature extraction
KW - Point cloud
UR - http://www.scopus.com/inward/record.url?scp=85075946526&partnerID=8YFLogxK
U2 - 10.1109/ISSC.2019.8904930
DO - 10.1109/ISSC.2019.8904930
M3 - Conference contribution
AN - SCOPUS:85075946526
T3 - 30th Irish Signals and Systems Conference, ISSC 2019
BT - 30th Irish Signals and Systems Conference, ISSC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 30th Irish Signals and Systems Conference, ISSC 2019
Y2 - 17 June 2019 through 18 June 2019
ER -