Please use this identifier to cite or link to this item: https://hdl.handle.net/10216/83597
Full metadata record
DC FieldValueLanguage
dc.creatorRoberta B. Oliveira
dc.creatorNorian Marranghello
dc.creatorAledir S. Pereira
dc.creatorJoão Manuel R. S. Tavares
dc.date.accessioned2019-02-08T09:46:53Z-
dc.date.available2019-02-08T09:46:53Z-
dc.date.issued2016
dc.identifier.issn0957-4174
dc.identifier.othersigarra:128722
dc.identifier.urihttps://repositorio-aberto.up.pt/handle/10216/83597-
dc.description.abstractSkin cancer is considered one of the most common types of cancer in several countries and its incidencerate has increased in recent years. Computational methods have been developed to assist dermatologistsin early diagnosis of skin cancer. Computational analysis of skin lesion images has become a challengingresearch area due to the difficulty in discerning some types of skin lesions. A novel computational approachis presented for extracting skin lesion features from images based on asymmetry, border, colourand texture analysis, in order to diagnose skin lesion types. The approach is based on an anisotropic diffusionfilter, an active contour model without edges and a support vector machine. Experiments wereperformed regarding the segmentation and classification of pigmented skin lesions in macroscopic images,with the results obtained being very promising.
dc.language.isoeng
dc.rightsopenAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.subjectCiências Tecnológicas, Ciências da engenharia e tecnologias
dc.subjectTechnological sciences, Engineering and technology
dc.titleA computational approach for detecting pigmented skin lesions in macroscopic images
dc.typeArtigo em Revista Científica Internacional
dc.contributor.uportoFaculdade de Engenharia
dc.identifier.doi10.1016/j.eswa.2016.05.017
dc.subject.fosCiências da engenharia e tecnologias
dc.subject.fosEngineering and technology
Appears in Collections:FEUP - Artigo em Revista Científica Internacional

Files in This Item:
File Description SizeFormat 
128722.1.png1st Page475.55 kBimage/pngView/Open
128722.pdfDraft Paper2.58 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons