TY - GEN
T1 - Heat-Map Based Emotion and Face Recognition from Thermal Images
AU - Ilikci, Burak
AU - Chen, Lei
AU - Cho, Hyuk
AU - Liu, Qingzhong
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Nowadays emotion recognition becomes feasible in the Computer Vision domain with the help of Convolutional Neural Networks. However, the credibility of emotion recognition from daily images or videos is evidently insufficient. As people can easily mimic emotions one after another by fooling the computational models, different defensive approaches should be taken into consideration. Particularly, thermal images taken by thermal cameras visualize the facial and body's heat status, revealing where humans actually feel emotions; therefore, models trained with thermal heat-maps are less subject to fake expressions. Accordingly, heat-maps provide suitable resources for developing more credible emotion recognition models. In this paper, a fast detection algorithm, YOLO, is adapted and trained to detect emotions in thermal images. The detection performance, in terms of average precision and intersection over union, from three detection algorithms, YOLO, ResNet, and DenseNet, is compared and their respective characteristics are discussed.
AB - Nowadays emotion recognition becomes feasible in the Computer Vision domain with the help of Convolutional Neural Networks. However, the credibility of emotion recognition from daily images or videos is evidently insufficient. As people can easily mimic emotions one after another by fooling the computational models, different defensive approaches should be taken into consideration. Particularly, thermal images taken by thermal cameras visualize the facial and body's heat status, revealing where humans actually feel emotions; therefore, models trained with thermal heat-maps are less subject to fake expressions. Accordingly, heat-maps provide suitable resources for developing more credible emotion recognition models. In this paper, a fast detection algorithm, YOLO, is adapted and trained to detect emotions in thermal images. The detection performance, in terms of average precision and intersection over union, from three detection algorithms, YOLO, ResNet, and DenseNet, is compared and their respective characteristics are discussed.
KW - Convolutional Neural Network
KW - Emotion recognition
KW - Thermal image
KW - YOLOv3
UR - http://www.scopus.com/inward/record.url?scp=85082240320&partnerID=8YFLogxK
U2 - 10.1109/ComComAp46287.2019.9018786
DO - 10.1109/ComComAp46287.2019.9018786
M3 - Conference article
AN - SCOPUS:85082240320
T3 - 2019 Computing, Communications and IoT Applications, ComComAp 2019
SP - 449
EP - 453
BT - 2019 Computing, Communications and IoT Applications, ComComAp 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Computing, Communications and IoT Applications, ComComAp 2019
Y2 - 26 October 2019 through 28 October 2019
ER -