Characterization of texture in image of skin lesions by support vector machine
| Contribuinte(s) |
Universidade Estadual Paulista (UNESP) |
|---|---|
| Data(s) |
27/05/2014
27/05/2014
19/11/2012
|
| Resumo |
Due 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. |
| Identificador |
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6263217 Iberian Conference on Information Systems and Technologies, CISTI. Information Systems and Technologies. New York: IEEE, p. 2, 2012. 2166-0727 2166-0735 http://hdl.handle.net/11449/73741 WOS:000319285900159 2-s2.0-84869038704 |
| Idioma(s) |
por |
| Relação |
Iberian Conference on Information Systems and Technologies, CISTI |
| Direitos |
closedAccess |
| Palavras-Chave | #box-counting method #fractal dimension #intelligent system #machine learning #support vector machine #Box-counting method #Feature vectors #Skin cancers #Skin lesion #Dermatology #Fractal dimension #Image retrieval #Information systems #Intelligent systems #Learning systems #Support vector machines #Textures #Image texture |
| Tipo |
info:eu-repo/semantics/conferencePaper |
