Subscription or Fee Access
A Novel Eigenborder-based Melanoma Diagnosis and Classification Algorithm in Dermoscopy Images
In this paper, a novel melanoma diagnosis and classification algorithm based on shape, texture, color and a new feature that is called eigenborder is proposed. In this algorithm, a modified level set algorithm is used to segment melanoma. In the feature extraction step, with regard to the border of the lesion, features such as Fourier coefficient descriptors is obtained from the location of the pixels on the specified border and eigenborders are extracted using Principle Component Analysis (PCA). Also, in addition to the features related to the color of the lesion, features of the tissue are extracted from the three sub-areas of central, middle, and marginal of lesion. Subsequently, in order to select the best features, a sequential forward selection algorithm, which is carried out based on the classification error by a classifier, is employed. Finally, considering the optimal selected features, Support Vector Machine (SVM) classifier is used to detect melanoma diagnosis. The proposed algorithm is obtained specificity of 92.3% and sensitivity of 94.1% on 642 images.
skin lesion, eigenborder, classification, Support Vector Machine, sequential forward selection, melanoma diagnosis detection.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.