A proposal of adaptive probabilistic model of context applied to visual recognition

Simple item page
datacite.alternateIdentifier.citationProceedings - International Conference of The Chilean Computer Science Society, SCCC, 2018-November, 2018
datacite.alternateIdentifier.doi10.1109/SCCC.2018.8705163
datacite.alternateIdentifier.issn1522-4902
datacite.creatorPeralta, Billy M.
datacite.creatorVergaray, Norman
datacite.creatorCaro, Luis Alberto
datacite.date2018
datacite.rightsRegistro bibliográfico
datacite.subjectBayesian Networks
datacite.subjectFunctional Optimization
datacite.subjectObject Recognition
datacite.subjectBayesian Networks
datacite.subjectDeep Learning
datacite.subjectErrors
datacite.subjectNewton-raphson Method
datacite.subjectNumerical Methods
datacite.subjectObject Recognition
datacite.subjectContext Modeling
datacite.subjectFunctional Optimization
datacite.subjectNumerical Approximations
datacite.subjectOccurrence Probability
datacite.subjectProbabilistic Modeling
datacite.subjectQuadratic Errors
datacite.subjectTesting Process
datacite.subjectVisual Recognition
datacite.subjectObject Detection
datacite.titleA proposal of adaptive probabilistic model of context applied to visual recognition
dc.date.accessioned2025-10-06T14:22:04Z
dc.date.available2025-10-06T14:22:04Z
dc.description.abstractWithin the increasing automation of tasks, it is necessary to obtain relevant information from images, to have clarity of the actions that must be performed. In this process, it is possible to detect objects individually, however this mode can generate a considerable error due to the enormous number of ways in which an object can be presented. It is therefore necessary to improve the level of accuracy, and a way to achieve this is taking into account the relationships between objects as well. Until now, context-oriented models generate relationships between objects without discriminating between input images. It is necessary that the model operates on each particular image, to reduce the error and obtain a conclusive result. In response to the above, this work proposes an adaptive probabilistic context-model. The model in question is a functional that processes the occurrence probability of the objects in each image, and generates the relations between the detectable objects using a Bayesian network in the form of a tree. This model is updated with the features of each image, requiring a minimization of the quadratic error through a numerical approximation, obtained by Newton-Raphson method. Comparisons were made between different heuristic proposals, as well as tests on different context-oriented databases, in order to validate the results. On the other hand, tests were performed using features extracted through histograms of orient gradients and Deep Learning. It was found that an improvement in the prediction of the order of 20% is feasible in the testing process. © 2019 Elsevier B.V., All rights reserved.
dc.description.ia_keywordobjects, model, context, necessary, error, each, image
dc.identifier.urihttps://repositoriodigital.uct.cl/handle/10925/6928
dc.language.isoen
dc.publisherIeee Computer Society
dc.relationinstname: ANID
dc.relationreponame: Repositorio Digital RI2.0
dc.rights.driverinfo:eu-repo/semantics/openAccess
dc.sourceProceedings - International Conference of The Chilean Computer Science Society, SCCC
dc.subject.ia_odsODS 4: Educación de calidad
dc.subject.ia_oecd1nCiencias Naturales
dc.subject.ia_oecd2nMatemáticas y Estadística
dc.subject.ia_oecd3nEstadística
dc.type.driverinfo:eu-repo/semantics/article
dc.type.driverhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.type.openaireinfo:eu-repo/semantics/publishedVersion
dspace.entity.typePublication
oaire.citationEdition2018
oaire.citationTitleProceedings - International Conference of The Chilean Computer Science Society, SCCC
oaire.fundingReferenceANID FONDECYT 11140892 (Iniciación)
oaire.licenseConditionCopyright © IEEE, 2018
oaire.resourceTypeComunicación de congreso
oaire.resourceType.enConference paper
uct.catalogadorjvu
uct.comunidadIngenieríaen_US
uct.departamentoDepartamento de Ingeniería Informática
uct.facultadFacultad de Ingeniería
uct.indizacionScopus
uct.indizacionEmerging Sources Citation Index - ESCI
uct.indizacionDBLP
uct.indizacionCrossRef
Files
Collections
Tecnologías de la Información