ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

An Improved Iterative Segmentation Algorithm using Canny Edge Detector for Skin Lesion Border Detection

Journal: The International Arab Journal of Information Technology (Vol.12, No. 4)

Publication Date:

Authors : ; ;

Page : 325-332

Keywords : Melanoma; canny edge detector; border detection; segmentation; skin lesion;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

One of the difficult problems recognized in image processing and pattern analysis, in particular in medical imaging applications is boundary detection. The detection of skin lesion boundaries accurately allows, skin cancer detection .There is no unified approach to this problem, which has been found to be application dependent. Early diagnosis of melanoma is a challenge, especially for general practitioners, as melanomas are hard to distinguish from common moles, even for experienced dermatologists. Melanoma can be cured by simple excision, when diagnosed at an early stage. Our proposed improved iterative segmentation algorithm, using canny edge detector, which is a simple and effective method to find the border of real skin lesions is presented, that helps in early detection of malignant melanoma and its performance is compared with the segmentation algorithm using canny detector [16] developed by us previously for border detection of real skin lesions. The experimental results demonstrate the successful border detection of noisy real skin lesions by our proposed improved iterative segmentation algorithm using canny detector. We conclude that our proposed segmentation algorithm, segments the lesion from the image even in the presence of noise for a variety of lesions and skin types and its performance is more reliable than the segmentation algorithm [16] that we have developed previously that uses canny detector, for border detection of real skin lesions for noisy skin lesion diagnosis.

Last modified: 2019-11-14 22:44:07