Please use this identifier to cite or link to this item: http://ir.lib.seu.ac.lk/handle/123456789/3512
Title: Optimal algorithm for melanoma skin cancer detection
Authors: Srirangan, S
Kariapper, R. K. Ahmadh Rifai
Keywords: Canny edge
Thresholding
Watershed
Issue Date: 15-Nov-2018
Publisher: Faculty of Applied Science, South Eastern University of Sri Lanka
Series/Report no.: Abstracts of the 7th Annual Science Research Sessions (ASRS) – 2018;03
Abstract: The skin cancer is one of the most Hazardous form of the Cancers found in the Humans today; especially, in the recent years, number of melanoma skin cancer patients have been recorded rapidly all over the world. The detection of Melanoma cancer in early stage can be helpful to cure it. However, the segmentation of the melanoma skin cancer lesion in traditional approach is a challenging task due to the number of false positives is large and time consuming in prediction. Hence, the development of automated computer vision system becoming as an essential. The aim in this study is to identify the specific cancer region with accuracy than traditional approaches. So, the objectives of this study are to examine existing systems and identify the major issues of the systems and finding future directions based on image processing techniques. The input to the system is the skin lesion image and then by applying novel image processing techniques. The finding of the study shows that, the new proposed approach could achieve 97.54% sensitivity, 97.69% specificity, and 97.56% accuracy respectively. This tool is more useful for the rural areas where the experts in the medical field may not be available. Since the tool is made more users friendly and robust for images acquired in any conditions, it can serve the purpose of automatic diagnostics of the melanoma Skin cancer.
URI: http://ir.lib.seu.ac.lk/handle/123456789/3512
ISBN: 9789556271362
Appears in Collections:ASRS - FAS 2018

Files in This Item:
File Description SizeFormat 
ASRS 2018-03.pdf191.31 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.