Improving Performance and Interpretability in Recognizing Facial Action Units with Deep Neural Networks

dc.contributor
Universitat de Barcelona. Departament de Matemàtiques i Informàtica
dc.contributor.author
Corneanu, Cipiran Adrian
dc.date.accessioned
2020-01-30T10:58:42Z
dc.date.available
2020-01-30T10:58:42Z
dc.date.issued
2019-12-13
dc.identifier.uri
http://hdl.handle.net/10803/668439
dc.description.abstract
Facial expressions are vital ways of communication between humans in social contexts. They are used as conversational markers and they convey information about affective and cognitive state. Many applications would benefit from the advance of automatic facial expression recognition (AFER). Robust AFER would improve human-computer interaction, it would increase driving safety, would help medical personal to better take care of patients with impaired communication ability and could transform online education. In recent years significant advancement has been undertaken in AFER with the use of deep neural networks (DNN). Unfortunately this increase in performance came with increased opacity. The current status of DNNs as "black-box" model hinders the advancement of the field. In this dissertation, we propose a new general framework for analysing deep neural networks based on the systematic study of their topology while they are learning patterns in the data. We use this framework to study a newly proposed DNN, specially built for Action Unit recognition which results in better understanding, control and increased performance. In summary, this dissertation has the following main contributions: a) Definition of comprehensive taxonomy of automatic computer vision approaches to automatic facial expression recognition followed by an extended review of historical and current trends in AFER. b) Proposal of a model that learns representation, patch and output structure of the face end-to-end e) Introduction of a structure inference topology that replicates inference algorithm in probabilistic graphical models by using a recurrent neural network c) Extended ablation study and experimental analysis of the newly proposed architecture d) Analysis and improving performance of the previously proposed architecture for facial expression architecture using the new theoretical framework. e) Formulation of novel general framework for analysis of deep neural networks based on algebraic topology f) Analysis of fundamental topological differences between DNNs that learn and DNNs that memorize g) Demonstrating the use of newly proposed analytical framework on facial action unit recognition using DSIN.
en_US
dc.format.extent
117 p.
en_US
dc.format.mimetype
application/pdf
dc.language.iso
eng
en_US
dc.publisher
Universitat de Barcelona
dc.rights.license
L'accés als continguts d'aquesta tesi queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by/4.0/
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
*
dc.source
TDX (Tesis Doctorals en Xarxa)
dc.subject
Reconeixement facial (Informàtica)
en_US
dc.subject
Reconocimiento facial (Informática)
en_US
dc.subject
Human face recognition (Computer science)
en_US
dc.subject.other
Ciències Experimentals i Matemàtiques
en_US
dc.title
Improving Performance and Interpretability in Recognizing Facial Action Units with Deep Neural Networks
en_US
dc.type
info:eu-repo/semantics/doctoralThesis
dc.type
info:eu-repo/semantics/publishedVersion
dc.subject.udc
62
en_US
dc.contributor.director
Escalera Guerrero, Sergio
dc.contributor.director
Madadi, Meysam
dc.contributor.tutor
Escalera Guerrero, Sergio
dc.embargo.terms
cap
en_US
dc.rights.accessLevel
info:eu-repo/semantics/openAccess


Documentos

CAC_PhD-THESIS.pdf

15.87Mb PDF

Este ítem aparece en la(s) siguiente(s) colección(ones)