Representation and retrieval of images by means of spatial relations between objects

dc.contributor.authorNUNES, D.
dc.contributor.authorFERREIRA, L. A.
dc.contributor.authorPaulo Santos
dc.contributor.authorPEASE, A.
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-8484-0354
dc.date.accessioned2023-08-26T23:48:06Z
dc.date.available2023-08-26T23:48:06Z
dc.date.issued2019-03-25
dc.description.abstractCopyright held by the author(s).The present work addresses the challenge of integrating low-level information with high-level knowledge (known as semantic gap) that exists in content-based image retrieval by introducing an approach to describe images by means of spatial relations. The proposed approach is called Image Retrieval using Region Analysis (IRRA) and relies on decomposing images into pairs of objects. This method generates a representation composed of n triples, each one containing: a noun, a preposition and, another noun. This representation paves the way to enable image retrieval based on spatial relations. Results for an indoor/outdoor classifier shows that neural networks alone are capable of achieving 88% in precision and recall, but when combined with ontology this result increases in 10 percentage points, reaching 98% of precision and recall.
dc.description.volume2350
dc.identifier.citationNUNES, D.; FERREIRA, L. A.; SANTOS, P.; PEASE, A. Representation and retrieval of images by means of spatial relations between objects. CEUR Workshop Proceedings, v. 2350, mar. 2019.
dc.identifier.issn1613-0073
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4889
dc.relation.ispartofCEUR Workshop Proceedings
dc.rightsAcesso Restrito
dc.titleRepresentation and retrieval of images by means of spatial relations between objects
dc.typeArtigo de evento
fei.scopus.citations0
fei.scopus.eid2-s2.0-85064993481
fei.scopus.subjectContent based image retrieval
fei.scopus.subjectHigh level knowledge
fei.scopus.subjectIndoor/outdoor
fei.scopus.subjectPercentage points
fei.scopus.subjectPrecision and recall
fei.scopus.subjectRegion analysis
fei.scopus.subjectSemantic gap
fei.scopus.subjectSpatial relations
fei.scopus.updated2024-09-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85064993481&origin=inward
Arquivos