Characterization of texture in image of skin lesions by support vector machine

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorOliveira, Roberta B.
dc.creatorCaldas Jr., Carlos Roberto D.
dc.creatorPereira, Aledir S.
dc.creatorGuido, Rodrigo C.
dc.creatorAraujo, Alex F. de
dc.creatorTavares, João Manuel R. S.
dc.creatorRossetti, Ricardo B.
dc.date2014-05-27T11:27:09Z
dc.date2016-10-25T18:39:03Z
dc.date2014-05-27T11:27:09Z
dc.date2016-10-25T18:39:03Z
dc.date2012-11-19
dc.date.accessioned2017-04-06T02:02:49Z
dc.date.available2017-04-06T02:02:49Z
dc.identifierIberian Conference on Information Systems and Technologies, CISTI. Information Systems and Technologies. New York: IEEE, p. 2, 2012.
dc.identifier2166-0727
dc.identifier2166-0735
dc.identifierhttp://hdl.handle.net/11449/73741
dc.identifierhttp://acervodigital.unesp.br/handle/11449/73741
dc.identifierWOS:000319285900159
dc.identifier2-s2.0-84869038704
dc.identifierhttp://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6263217
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/894526
dc.descriptionDue to the increased incidence of skin cancer, computational methods based on intelligent approaches have been developed to aid dermatologists in the diagnosis of skin lesions. This paper proposes a method to classify texture in images, since it is an important feature for the successfully identification of skin lesions. For this is defined a feature vector, with the fractal dimension of images through the box-counting method (BCM), which is used with a SVM to classify the texture of the lesions in to non-irregular or irregular. With the proposed solution, we could obtain an accuracy of 72.84%. © 2012 AISTI.
dc.languagepor
dc.relationIberian Conference on Information Systems and Technologies, CISTI
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectbox-counting method
dc.subjectfractal dimension
dc.subjectintelligent system
dc.subjectmachine learning
dc.subjectsupport vector machine
dc.subjectBox-counting method
dc.subjectFeature vectors
dc.subjectSkin cancers
dc.subjectSkin lesion
dc.subjectDermatology
dc.subjectFractal dimension
dc.subjectImage retrieval
dc.subjectInformation systems
dc.subjectIntelligent systems
dc.subjectLearning systems
dc.subjectSupport vector machines
dc.subjectTextures
dc.subjectImage texture
dc.titleCharacterization of texture in image of skin lesions by support vector machine
dc.typeOtro


Este ítem pertenece a la siguiente institución