Applying deep learning for food image analysis

Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2019, Tutor: Petia Radeva

Detalles Bibliográficos
Autor: Marrugat Torregrosa, Gerard
Tipo de recurso: tesis de maestría
Fecha de publicación:2019
País:España
Institución:Universidad de Barcelona
Repositorio:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/160143
Acceso en línea:https://hdl.handle.net/2445/160143
Access Level:acceso abierto
Palabra clave:Visió per ordinador
Xarxes neuronals (Informàtica)
Treballs de fi de màster
Sistemes classificadors (Intel·ligència artificial)
Aliments
Aprenentatge automàtic
Computer vision
Neural networks (Computer science)
Master's theses
Learning classifier systems
Food
Machine learning
id ES_8a4e31ae19e515dc51e63506abcbb565
oai_identifier_str oai:diposit.ub.edu:2445/160143
network_acronym_str ES
network_name_str España
repository_id_str
spelling Applying deep learning for food image analysisMarrugat Torregrosa, GerardVisió per ordinadorXarxes neuronals (Informàtica)Treballs de fi de màsterSistemes classificadors (Intel·ligència artificial)AlimentsAprenentatge automàticComputer visionNeural networks (Computer science)Master's thesesLearning classifier systemsFoodMachine learningTreballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2019, Tutor: Petia Radeva[en] Food is an important component in people’s daily life, examples of the previous assertion are the range of possible diets according to the animal or vegetal origin, the intolerance to some aliments and lately the increasing number of food pictures in social networks. Several computer vision approaches have been proposed for tackling food analysis problems, but few effort has been done in taking benefit of the hierarchical relation between elements in a food image; dish and ingredients. In this project the highly performing state of the art CNN method is adapted concatenating an ontology layer, a multidimensional layer which contains the relation between the elements, in order to help during the classification process. Different structures for the ontology have been tested to prove which relations have the most beneficial impact, and which are less relevant. Additionally to structure, the value of the elements that compound this hierarchical relation layer play an important role, therefore the experiments performed contained different weighted relations between the components. The ontology layer is built with the labels of the multiple task in the dataset used to train the model. At the end, the results obtained will be compared to a baseline model without the ontology layer and it will be appreciated how hierarchical relations between tasks benefits classification. Finally, the result will be a model which will be able to simultaneously predict two food-related tasks; dish and ingredients.Radeva, Petia2019info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2445/160143Màster Oficial - Fonaments de la Ciència de Dadesreponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaIngléscc-by-sa (c) Gerard Marrugat Torregrosa, 2019codi: GPL (c) Gerard Marrugat Torregrosa, 2019http://creativecommons.org/licenses/by-sa/3.0/es/http://www.gnu.org/licenses/gpl-3.0.ca.htmlinfo:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/1601432026-05-27T06:46:51Z
dc.title.none.fl_str_mv Applying deep learning for food image analysis
title Applying deep learning for food image analysis
spellingShingle Applying deep learning for food image analysis
Marrugat Torregrosa, Gerard
Visió per ordinador
Xarxes neuronals (Informàtica)
Treballs de fi de màster
Sistemes classificadors (Intel·ligència artificial)
Aliments
Aprenentatge automàtic
Computer vision
Neural networks (Computer science)
Master's theses
Learning classifier systems
Food
Machine learning
title_short Applying deep learning for food image analysis
title_full Applying deep learning for food image analysis
title_fullStr Applying deep learning for food image analysis
title_full_unstemmed Applying deep learning for food image analysis
title_sort Applying deep learning for food image analysis
dc.creator.none.fl_str_mv Marrugat Torregrosa, Gerard
author Marrugat Torregrosa, Gerard
author_facet Marrugat Torregrosa, Gerard
author_role author
dc.contributor.none.fl_str_mv Radeva, Petia
dc.subject.none.fl_str_mv Visió per ordinador
Xarxes neuronals (Informàtica)
Treballs de fi de màster
Sistemes classificadors (Intel·ligència artificial)
Aliments
Aprenentatge automàtic
Computer vision
Neural networks (Computer science)
Master's theses
Learning classifier systems
Food
Machine learning
topic Visió per ordinador
Xarxes neuronals (Informàtica)
Treballs de fi de màster
Sistemes classificadors (Intel·ligència artificial)
Aliments
Aprenentatge automàtic
Computer vision
Neural networks (Computer science)
Master's theses
Learning classifier systems
Food
Machine learning
description Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2019, Tutor: Petia Radeva
publishDate 2019
dc.date.none.fl_str_mv 2019
dc.type.none.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2445/160143
url https://hdl.handle.net/2445/160143
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv cc-by-sa (c) Gerard Marrugat Torregrosa, 2019
codi: GPL (c) Gerard Marrugat Torregrosa, 2019
http://creativecommons.org/licenses/by-sa/3.0/es/
http://www.gnu.org/licenses/gpl-3.0.ca.html
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by-sa (c) Gerard Marrugat Torregrosa, 2019
codi: GPL (c) Gerard Marrugat Torregrosa, 2019
http://creativecommons.org/licenses/by-sa/3.0/es/
http://www.gnu.org/licenses/gpl-3.0.ca.html
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv Màster Oficial - Fonaments de la Ciència de Dades
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412706078949377
score 15,300719

Similares en LA Referencia