Standard
Applying Delaunay triangulation augmentation for deep learning facial expression generation and recognition. /
Valev, Hristo; Gallucci, Alessio ; Leufkens, Tim et al.
Pattern Recognition. ICPR International Workshops and Challenges : Virtual Event, January 10–15, 2021, Proceedings, Part III. ed. / Alberto Del Bimbo; Rita Cucchiara; Stan Sclaroff; Giovanni Maria Farinella; Tao Mei; Marco Bertini; Hugo Jair Escalante; Roberto Vezzani. Cham: Springer, 2021. p. 730-740 (Lecture Notes in Computer Science; Vol. 12663).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Valev, H, Gallucci, A, Leufkens, T, Westerink, J
& Sas, C 2021,
Applying Delaunay triangulation augmentation for deep learning facial expression generation and recognition. in A Del Bimbo, R Cucchiara, S Sclaroff, GM Farinella, T Mei, M Bertini, HJ Escalante & R Vezzani (eds),
Pattern Recognition. ICPR International Workshops and Challenges : Virtual Event, January 10–15, 2021, Proceedings, Part III. Lecture Notes in Computer Science, vol. 12663, Springer, Cham, pp. 730-740.
https://doi.org/10.1007/978-3-030-68796-0_53
APA
Valev, H., Gallucci, A., Leufkens, T., Westerink, J.
, & Sas, C. (2021).
Applying Delaunay triangulation augmentation for deep learning facial expression generation and recognition. In A. Del Bimbo, R. Cucchiara, S. Sclaroff, G. M. Farinella, T. Mei, M. Bertini, H. J. Escalante, & R. Vezzani (Eds.),
Pattern Recognition. ICPR International Workshops and Challenges : Virtual Event, January 10–15, 2021, Proceedings, Part III (pp. 730-740). (Lecture Notes in Computer Science; Vol. 12663). Springer.
https://doi.org/10.1007/978-3-030-68796-0_53
Vancouver
Valev H, Gallucci A, Leufkens T, Westerink J
, Sas C.
Applying Delaunay triangulation augmentation for deep learning facial expression generation and recognition. In Del Bimbo A, Cucchiara R, Sclaroff S, Farinella GM, Mei T, Bertini M, Escalante HJ, Vezzani R, editors, Pattern Recognition. ICPR International Workshops and Challenges : Virtual Event, January 10–15, 2021, Proceedings, Part III. Cham: Springer. 2021. p. 730-740. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-68796-0_53
Author
Bibtex
@inproceedings{2ae1c54feadd47c3ac82c0b8266a4405,
title = "Applying Delaunay triangulation augmentation for deep learning facial expression generation and recognition",
abstract = "Generating and recognizing facial expressions has numerous applications, however, those are limited by the scarcity of datasets containing labeled nuanced expressions. In this paper, we describe the use of Delaunay triangulation combined with simple morphing techniques to blend images of faces, which allows us to create and automatically label facial expressions portraying controllable intensities of emotion. We have applied this approach on the RafD dataset consisting of 67 participants and 8 categorical emotions and evaluated the augmentation in a facial expression generation and recognition tasks using deep learning models. For the generation task, we used a deconvolution neural network which learns to encode the input images in a high-dimensional feature space and generate realistic expressions at varying intensities. The augmentation significantly improves the quality of images compared to previous comparable experiments and it allows to create images with a higher resolution. For the recognition task, we evaluated pre-trained Densenet121 and Resnet50 networks with either the original or augmented dataset. Our results indicate that the augmentation alone has a similar or better performance compared to the original. Implications of this method and its role in improving existing facial expression generation and recognition approaches are discussed.",
author = "Hristo Valev and Alessio Gallucci and Tim Leufkens and Joyce Westerink and Corina Sas",
year = "2021",
month = feb,
day = "21",
doi = "10.1007/978-3-030-68796-0_53",
language = "English",
isbn = "9783030687953",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "730--740",
editor = "{Del Bimbo}, Alberto and Rita Cucchiara and Stan Sclaroff and Farinella, {Giovanni Maria} and Tao Mei and Marco Bertini and Escalante, {Hugo Jair} and Roberto Vezzani",
booktitle = "Pattern Recognition. ICPR International Workshops and Challenges",
}
RIS
TY - GEN
T1 - Applying Delaunay triangulation augmentation for deep learning facial expression generation and recognition
AU - Valev, Hristo
AU - Gallucci, Alessio
AU - Leufkens, Tim
AU - Westerink, Joyce
AU - Sas, Corina
PY - 2021/2/21
Y1 - 2021/2/21
N2 - Generating and recognizing facial expressions has numerous applications, however, those are limited by the scarcity of datasets containing labeled nuanced expressions. In this paper, we describe the use of Delaunay triangulation combined with simple morphing techniques to blend images of faces, which allows us to create and automatically label facial expressions portraying controllable intensities of emotion. We have applied this approach on the RafD dataset consisting of 67 participants and 8 categorical emotions and evaluated the augmentation in a facial expression generation and recognition tasks using deep learning models. For the generation task, we used a deconvolution neural network which learns to encode the input images in a high-dimensional feature space and generate realistic expressions at varying intensities. The augmentation significantly improves the quality of images compared to previous comparable experiments and it allows to create images with a higher resolution. For the recognition task, we evaluated pre-trained Densenet121 and Resnet50 networks with either the original or augmented dataset. Our results indicate that the augmentation alone has a similar or better performance compared to the original. Implications of this method and its role in improving existing facial expression generation and recognition approaches are discussed.
AB - Generating and recognizing facial expressions has numerous applications, however, those are limited by the scarcity of datasets containing labeled nuanced expressions. In this paper, we describe the use of Delaunay triangulation combined with simple morphing techniques to blend images of faces, which allows us to create and automatically label facial expressions portraying controllable intensities of emotion. We have applied this approach on the RafD dataset consisting of 67 participants and 8 categorical emotions and evaluated the augmentation in a facial expression generation and recognition tasks using deep learning models. For the generation task, we used a deconvolution neural network which learns to encode the input images in a high-dimensional feature space and generate realistic expressions at varying intensities. The augmentation significantly improves the quality of images compared to previous comparable experiments and it allows to create images with a higher resolution. For the recognition task, we evaluated pre-trained Densenet121 and Resnet50 networks with either the original or augmented dataset. Our results indicate that the augmentation alone has a similar or better performance compared to the original. Implications of this method and its role in improving existing facial expression generation and recognition approaches are discussed.
U2 - 10.1007/978-3-030-68796-0_53
DO - 10.1007/978-3-030-68796-0_53
M3 - Conference contribution/Paper
SN - 9783030687953
T3 - Lecture Notes in Computer Science
SP - 730
EP - 740
BT - Pattern Recognition. ICPR International Workshops and Challenges
A2 - Del Bimbo, Alberto
A2 - Cucchiara, Rita
A2 - Sclaroff, Stan
A2 - Farinella, Giovanni Maria
A2 - Mei, Tao
A2 - Bertini, Marco
A2 - Escalante, Hugo Jair
A2 - Vezzani, Roberto
PB - Springer
CY - Cham
ER -
