Files

codi_font.zip (29.38 KB)
171974.pdf (15 MB)

Document type

Bachelor thesis

Publication date

2020-09-13

Publication license

memòria: cc-nc-nd (c) Jorge Acosta Hernández, 2020
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/171974

Neutral face generator using variational autoencoders

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

Abstract

[en] The aim of this project is to develop a model which is able to generate a neutral face from a sample of images of the same person with different expressions. This expressions can be gathered from a video of that person just talking frontally to the camera. For doing this we will need a model which as it is able to learn meaningful features of the frontal faces. Also this model should be capable of reconstructing faces from this learned features.

Description

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2020, Director: Meysam Madadi

Subject

Aprenentatge automàtic, Xarxes neuronals (Informàtica), Programari, Treballs de fi de grau, Reconeixement facial (Informàtica), Expressió facial

Subject (English)

Machine learning, Neural networks (Computer science), Computer software, Human face recognition (Computer science), Facial expression, Bachelor's theses

Citation

Collections

Treballs Finals de Grau (TFG) - Enginyeria Informàtica
Programari - Treballs de l'alumnat

Citation

ACOSTA HERNÁNDEZ, Jorge. Neutral face generator using variational autoencoders. [consulted: 13 of June of 2026]. Available at: https://hdl.handle.net/2445/171974

Export metadata

JSON - METS

Share record