Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes

l Laboratorio de Sueño y Memoria from Instituto Tecnológico de Buenos Aires (ITBA) studies the formation of false memories, and how these can be reduced or modified, and is in collaboration with the Innocence Project to investigate how these can lead to errors in convictions. From this research, the...

Descripción completa

Detalles Bibliográficos
Autores principales: Lozano, Jimena, Herrán Oyhanarte, Maite Mercedes
Otros Autores: Ramele, Rodrigo
Formato: Proyecto final de Grado
Lenguaje:Inglés
Publicado: 2022
Materias:
FALSAS MEMORIAS
PROCESAMIENTO DE IMAGENES
INTELIGENCIA ARTIFICIAL
RECONOCIMIENTO FACIAL
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/3800
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-3800
record_format dspace
spelling I32-R138-123456789-38002022-12-07T14:33:59Z Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes Lozano, Jimena Herrán Oyhanarte, Maite Mercedes Ramele, Rodrigo FALSAS MEMORIAS PROCESAMIENTO DE IMAGENES INTELIGENCIA ARTIFICIAL RECONOCIMIENTO FACIAL l Laboratorio de Sueño y Memoria from Instituto Tecnológico de Buenos Aires (ITBA) studies the formation of false memories, and how these can be reduced or modified, and is in collaboration with the Innocence Project to investigate how these can lead to errors in convictions. From this research, the need arises to carry out experiments with human faces that are similar to each other, and how this similarity can result in the formation of false memories. In this project, we investigate a field of Artificial Intelligence (AI), Deep Learning, which can provide us with a solution to the generation of artificial faces. In particular, we implement a face generation model using a Generative Adversarial Network (GAN), with the aim of generating faces as realistic as possible, so that a human cannot distinguish them from real faces. StyleGAN, a particular implementation of the GAN network, was the chosen architecture, because in addition to producing images with high resolution quality, it presents a model that allows navigation of the latent space and the synthesis of faces, using style mixing properties. Finally, an application called FG-Style was developed and installed on a GPU-based server at ITBA so that the laboratory can have control over the face generation model, and over the generation of faces similar to a selected one, using StyleGAN’s style mixing properties to have a grip over the change of specific features of the generated faces." Proyecto final Ingeniería Informática (grado) - Instituto Tecnológico de Buenos Aires, Buenos Aires, 2021 2022-04-19T18:07:08Z 2022-04-19T18:07:08Z 2021-11-16 Proyecto final de Grado http://ri.itba.edu.ar/handle/123456789/3800 en application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Inglés
topic FALSAS MEMORIAS
PROCESAMIENTO DE IMAGENES
INTELIGENCIA ARTIFICIAL
RECONOCIMIENTO FACIAL
spellingShingle FALSAS MEMORIAS
PROCESAMIENTO DE IMAGENES
INTELIGENCIA ARTIFICIAL
RECONOCIMIENTO FACIAL
Lozano, Jimena
Herrán Oyhanarte, Maite Mercedes
Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes
topic_facet FALSAS MEMORIAS
PROCESAMIENTO DE IMAGENES
INTELIGENCIA ARTIFICIAL
RECONOCIMIENTO FACIAL
description l Laboratorio de Sueño y Memoria from Instituto Tecnológico de Buenos Aires (ITBA) studies the formation of false memories, and how these can be reduced or modified, and is in collaboration with the Innocence Project to investigate how these can lead to errors in convictions. From this research, the need arises to carry out experiments with human faces that are similar to each other, and how this similarity can result in the formation of false memories. In this project, we investigate a field of Artificial Intelligence (AI), Deep Learning, which can provide us with a solution to the generation of artificial faces. In particular, we implement a face generation model using a Generative Adversarial Network (GAN), with the aim of generating faces as realistic as possible, so that a human cannot distinguish them from real faces. StyleGAN, a particular implementation of the GAN network, was the chosen architecture, because in addition to producing images with high resolution quality, it presents a model that allows navigation of the latent space and the synthesis of faces, using style mixing properties. Finally, an application called FG-Style was developed and installed on a GPU-based server at ITBA so that the laboratory can have control over the face generation model, and over the generation of faces similar to a selected one, using StyleGAN’s style mixing properties to have a grip over the change of specific features of the generated faces."
author2 Ramele, Rodrigo
author_facet Ramele, Rodrigo
Lozano, Jimena
Herrán Oyhanarte, Maite Mercedes
format Proyecto final de Grado
author Lozano, Jimena
Herrán Oyhanarte, Maite Mercedes
author_sort Lozano, Jimena
title Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes
title_short Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes
title_full Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes
title_fullStr Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes
title_full_unstemmed Use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of StyleGAN’s generative image modeling and style mixing properties to design an interface for experimentation purposes
title_sort use of generative adversarial networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases: implementation of stylegan’s generative image modeling and style mixing properties to design an interface for experimentation purposes
publishDate 2022
url http://ri.itba.edu.ar/handle/123456789/3800
work_keys_str_mv AT lozanojimena useofgenerativeadversarialnetworksforthecreationandmanipulationoffacialimagesinthecontextofstudyingfalsememoriesanditseffectsonwrongfulconvictioncasesimplementationofstylegansgenerativeimagemodelingandstylemixingpropertiestodesignaninterfaceforexperimenta
AT herranoyhanartemaitemercedes useofgenerativeadversarialnetworksforthecreationandmanipulationoffacialimagesinthecontextofstudyingfalsememoriesanditseffectsonwrongfulconvictioncasesimplementationofstylegansgenerativeimagemodelingandstylemixingpropertiestodesignaninterfaceforexperimenta
_version_ 1765660878939619328

Ejemplares similares