Skin Cancer Classification using Machine Learning for Dermoscopy Image
Sanket Kumar1, Chandra J2
1Sanket Kumar, P.G. Scholar, Department of Computer Science, CHRIST (Deemed to Be University), Bangalore (Karnataka), India.
2Dr.Chandra J, Associate Professor, Department of Computer Science, CHRIST (Deemed to Be University), Bangalore (Karnataka), India.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 1456-1462 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5676058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: 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%.
Keyword: Support Vector Machine (SVM), K -Nearest Neighbour (KNN), Gray Level Co-occurrence Matrix (GLCM), Median Filter, Weiner Filter, Thresholding.
Scope of the Article: Classification.