A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm

Detalhes bibliográficos
Autor(a) principal: Monteiro, Rui Filipe Martins
Data de Publicação: 2023
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/148921
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
id RCAP_0a4cc33fb08ea069977a9dfc3a24cd21
oai_identifier_str oai:run.unl.pt:10362/148921
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary AlgorithmComputer VisionGenetic ProgrammingDeep LearningConvolutional Neural NetworksDomínio/Área Científica::Ciências Naturais::Ciências da Computação e da InformaçãoDissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data ScienceComputer Vision is a sub-field of Artificial Intelligence that provides a visual perception component to computers, mimicking human intelligence. One of its tasks is image classification and Convolutional Neural Networks (CNNs) have been the most implemented algorithm in the last few years, with few changes made to the fully-connected layer of those neural networks. Nonetheless, recent research has been showing their accuracy could be improved in certain cases by implementing other algorithms for the classification of high-level image features from convolutional layers. Thus, the main research question for this document is: To what extent does the substitution of the fully-connected layer in Convolutional Neural Networks for an evolutionary algorithm affect the performance of those CNN models? The proposed two-step approach in this study does the classification of high-level image features with a state-of-the-art GP-based algorithm for multiclass classification called M4GP. This is conducted using secondary data with different characteristics, to better benchmark the implementation and to carefully investigate different outcomes. Results indicate the new learning approach yielded similar performance in the dataset with a low number of output classes. However, none of the M4GP models was able to surpass the results of the fully-connected layers in terms of test accuracy. Even so, this might be an interesting route if one has a powerful computer and needs a very light classifier in terms of model size. The results help to understand in which situation it might be beneficial to perform a similar experimental setup, either in the context of a work project or concerning a novel research topic.Castelli, MauroVanneschi, LeonardoRUNMonteiro, Rui Filipe Martins2023-02-09T15:40:06Z2023-01-242023-01-24T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/148921TID:203219112enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:30:41Zoai:run.unl.pt:10362/148921Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:53:33.290108Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
title A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
spellingShingle A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
Monteiro, Rui Filipe Martins
Computer Vision
Genetic Programming
Deep Learning
Convolutional Neural Networks
Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação
title_short A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
title_full A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
title_fullStr A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
title_full_unstemmed A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
title_sort A Genetic Programming Approach for Computer Vision: Classifying High-level Image Features from Convolutional Layers with an Evolutionary Algorithm
author Monteiro, Rui Filipe Martins
author_facet Monteiro, Rui Filipe Martins
author_role author
dc.contributor.none.fl_str_mv Castelli, Mauro
Vanneschi, Leonardo
RUN
dc.contributor.author.fl_str_mv Monteiro, Rui Filipe Martins
dc.subject.por.fl_str_mv Computer Vision
Genetic Programming
Deep Learning
Convolutional Neural Networks
Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação
topic Computer Vision
Genetic Programming
Deep Learning
Convolutional Neural Networks
Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação
description Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
publishDate 2023
dc.date.none.fl_str_mv 2023-02-09T15:40:06Z
2023-01-24
2023-01-24T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/148921
TID:203219112
url http://hdl.handle.net/10362/148921
identifier_str_mv TID:203219112
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138125993213952

Registros relacionados