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

Author

Oliveira, Roberta B. ; Caldas, C.R.D. ; Pereira, Aledir S. ; Guido, Rodrigo C. ; De Araujo, Alex F. ; Tavares, João Manuel R S ; Rossetti, Ricardo B.

Author_Institution

Dept. de Cienc. de Comput. e Estatisticas, UNESP, São José do Rio Preto, Brazil

fYear

2012

fDate

20-23 June 2012

Firstpage

1

Lastpage

2

Abstract

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%.

Keywords

image classification; image texture; skin; support vector machines; BCM; box counting method; computational methods; image texture; intelligent approaches; skin cancer; skin lesions; support vector machine; texture classification; Dermis; Fractals; Image segmentation; Lesions; Malignant tumors; Support vector machines; box-counting method; fractal dimension; intelligent system; machine learning; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Systems and Technologies (CISTI), 2012 7th Iberian Conference on

Conference_Location

Madrid

ISSN

2166-0727

Print_ISBN

978-1-4673-2843-2

Type

conf

Filename

6263217