Export Ready — 

Soft computing for Ill Posed Problems in Computer Vision

Bibliographic Details
Main Author: Bakurov, Illya Olegovich
Publication Date: 2022
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/144500
Summary: A thesis submitted in partial fulfillment of the requirements for the degree of Doctor in Information Management, specialization in Information and Decision Systems
id RCAP_ddbb28dc7218c151146a6e125e3ac4d1
oai_identifier_str oai:run.unl.pt:10362/144500
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Soft computing for Ill Posed Problems in Computer VisionEvolutionary ComputationSwarm IntelligenceGenetic ProgrammingEnsemble LearningStackingComputer VisionFull Reference Image Quality AssessmentSemantic SegmentationA thesis submitted in partial fulfillment of the requirements for the degree of Doctor in Information Management, specialization in Information and Decision SystemsSoft computing (SC) includes computational techniques that are tolerant of approximations, missing information, and uncertainty, and aim at providing effective and efficient solutions to problems which may be unsolvable, or too time-consuming to solve, with exhaustive techniques. SC has found many applications in various domains of research and industry, including computer vision (CV). This dissertation focuses on tasks of fullreference image quality assessment (FR-IQA) and fast scene understanding (FSU). The former consists of assessing images’ visual quality in regard to some pristine reference. The latter consists of classifying each pixel of a scene assuming a rapidly changing environment like, for instance, in a self-driving car. The current state-of-the-art (SOTA) in both FR-IQA and FSU rely upon convolutional neural networks (CNNs), which can be seen as a computational metaphor of the human visual cortex. Although CNNs achieved unprecedented results in many CV tasks, they also present several drawbacks: massive amounts of data and processing resources for training; the difficulty of outputs’ interpretation; reduced usability for compact battery-powered devices... This dissertation addresses FR-IQA and FSU using SC techniques other than CNNs. Initially, we created a flexible and efficient library to support our endeavors; it is publicly available and implements a wide range of metaheuristics to solve different problems. Then, we used swarm and evolutionary computation to optimize the parameters of several traditional FR-IQA measures (FR-IQAMs) that integrate the socalled structural similarity paradigm; the novel parameters improve measures’ precision without affecting their complexity. Afterward, we applied genetic programming (GP) to automatically formulate novel FR-IQAMs that are simultaneously simple, accurate, and interpretable. Lastly, we used GP as a meta-model for stacking efficient CNNs for FSU; the approach allowed us to obtain simple and interpretable models that did not exceed processing preconditions for real-time applications while achieving high levels of precision.Castelli, MauroVanneschi, LeonardoSchettini, RaimondoRUNBakurov, Illya Olegovich2023-09-19T00:32:37Z2022-09-192022-09-19T00:00:00Zdoctoral thesisinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10362/144500TID:101644035enginfo:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:05:48Zoai:run.unl.pt:10362/144500Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:36:15.218233Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Soft computing for Ill Posed Problems in Computer Vision
title Soft computing for Ill Posed Problems in Computer Vision
spellingShingle Soft computing for Ill Posed Problems in Computer Vision
Bakurov, Illya Olegovich
Evolutionary Computation
Swarm Intelligence
Genetic Programming
Ensemble Learning
Stacking
Computer Vision
Full Reference Image Quality Assessment
Semantic Segmentation
title_short Soft computing for Ill Posed Problems in Computer Vision
title_full Soft computing for Ill Posed Problems in Computer Vision
title_fullStr Soft computing for Ill Posed Problems in Computer Vision
title_full_unstemmed Soft computing for Ill Posed Problems in Computer Vision
title_sort Soft computing for Ill Posed Problems in Computer Vision
author Bakurov, Illya Olegovich
author_facet Bakurov, Illya Olegovich
author_role author
dc.contributor.none.fl_str_mv Castelli, Mauro
Vanneschi, Leonardo
Schettini, Raimondo
RUN
dc.contributor.author.fl_str_mv Bakurov, Illya Olegovich
dc.subject.por.fl_str_mv Evolutionary Computation
Swarm Intelligence
Genetic Programming
Ensemble Learning
Stacking
Computer Vision
Full Reference Image Quality Assessment
Semantic Segmentation
topic Evolutionary Computation
Swarm Intelligence
Genetic Programming
Ensemble Learning
Stacking
Computer Vision
Full Reference Image Quality Assessment
Semantic Segmentation
description A thesis submitted in partial fulfillment of the requirements for the degree of Doctor in Information Management, specialization in Information and Decision Systems
publishDate 2022
dc.date.none.fl_str_mv 2022-09-19
2022-09-19T00:00:00Z
2023-09-19T00:32:37Z
dc.type.driver.fl_str_mv doctoral thesis
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/144500
TID:101644035
url http://hdl.handle.net/10362/144500
identifier_str_mv TID:101644035
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:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596828447145984

Similar Items