Applying Delaunay Triangulation Augmentation for Deep Learning Facial Expression Generation and Recognition

Hristo Valev, Alessio Gallucci, Tim Leufkens, Joyce Westerink, Corina Sas

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

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.

Originele taal-2Engels
TitelPattern Recognition ICPR International Workshops and Challenges
SubtitelVirtual Event, January 10–15, 2021, Proceedings, Part III
RedacteurenAlberto Del Bimbo, Rita Cucchiara, Stan Sclaroff, Giovanni Maria Farinella, Tao Mei, Marco Bertini, Hugo Jair Escalante, Roberto Vezzani
Plaats van productieCham
UitgeverijSpringer
Pagina's730-740
Aantal pagina's11
ISBN van elektronische versie978-3-030-68796-0
ISBN van geprinte versie978-3-030-68795-3
DOI's
StatusGepubliceerd - 2021
Evenement25th International Conference on Pattern Recognition Workshops, ICPR 2020 - Milan, Italië
Duur: 10 jan 202115 jan 2021
Congresnummer: 25
https://www.micc.unifi.it/icpr2020/

Publicatie series

NaamLecture Notes in Computer Science (LNCS)
Volume12633
ISSN van geprinte versie0302-9743
ISSN van elektronische versie1611-3349
Naam Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)
Volume12663

Congres

Congres25th International Conference on Pattern Recognition Workshops, ICPR 2020
Verkorte titelICPR 2020
LandItalië
StadMilan
Periode10/01/2115/01/21
Internet adres

Bibliografische nota

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.

Vingerafdruk

Duik in de onderzoeksthema's van 'Applying Delaunay Triangulation Augmentation for Deep Learning Facial Expression Generation and Recognition'. Samen vormen ze een unieke vingerafdruk.

Citeer dit