Skin cancer classification using machine learning for dermoscopy image

Title

Skin cancer classification using machine learning for dermoscopy image

Creator

Kumar S.; Chandra J.

Description

Skin cancer is highly ambiguous and difficult to identify and cure in the last stage. To increase the survival rate, it is important to recognize the stages of skin cancer for effective treatment. The main aim of the paper is to classify the various stages of skin cancer using dermoscopy images from the data repository of ISIC and PH2. The data is pre -processed with the help of median filter and wiener filter for removing the noise. Segmentation is processed using Watershed and Morphological. After the segmentation, features were extracted using Grey Level Co-occurrence Matrix (GLCM), Color, Geometrical shapes in order to improve the accuracy of dermoscopy image. Finally, the dataset is classified with some popular methods like KNN with 89%, Ensemble with 84% and SVM works better than the other two methods by giving the highest accuracy of 92%. BEIESP.

Source

International Journal of Innovative Technology and Exploring Engineering, Vol-8, No. 7, pp. 1456-1462.

Date

2019-01-01

Publisher

Blue Eyes Intelligence Engineering and Sciences Publication

Subject

Gray Level Co-occurrence Matrix (GLCM); K -Nearest Neighbour (KNN); Median Filter; Support Vector Machine (SVM); Thresholding; Weiner Filter

Coverage

Kumar S., Department of Computer Science, CHRIST (Deemed to be University), Bangalore, Karnataka, India; Chandra J., Department of Computer Science, CHRIST (Deemed to be University), Bangalore, Karnataka, India

Rights

Restricted Access

Relation

ISSN: 22783075

Format

Online

Language

English

Type

Article

Identifier

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067876244&partnerID=40&md5=d046ce210431980e588992195568f383