Open AccessAutomated Framework for Segmenting Skin Lesions using Artificial Bee Colony Optimization with Morphological Reconstruction
Author(s) -
R. Sumathi,
M. Venkatesulu
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a1106.1291s419
Subject(s) - artificial intelligence , segmentation , preprocessor , pattern recognition (psychology) , computer science , noise (video) , cluster analysis , pixel , level set (data structures) , image segmentation , median filter , computer vision , image processing , image (mathematics)
Nowadays, Many people are affected by skin cancers. Our proposed work designed a framework to extract the skin cancer using artificial bee colony with morphological reconstruction filters, which helps the demonologist to prevent the severity in early stage, Melanoma is the now become a harmful form of skin cancer which leads the skin cells to grow rapidly and form cancerous tumors. We collected various melanoma images from having used samples from public dataset like ISIC archive and a few from clinical datasets. To remove the noise, median filtering is used for preprocessing in the first step, to segment the tumor boundary Artificial bee colony is used and to remove the unwanted pixels using morphological reconstruction filters. Segmentation metrics like precision, recall, accuracy, Mean Square Error, Peak signal to noise ratio and computational time were calculated. Our proposed method yield 97.7% segmentation accuracy when compared with the level set method and Fuzzy C Means clustering techniques