Detection of Malignant Skin Disease Based on Lesion Segmentation – A Survey
Kailas Tambe1, G. Krishna Mohan2
1Kailas Tam, Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam, Erode (Tamil Nadu), India.
2Dr. G. Krishna Mohan, Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam, Erode (Tamil Nadu), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 22 December 2018 | Manuscript Published on 30 December 2018 | PP: 70-76 | Volume-8 Issue-2S, December 2018 | Retrieval Number: 100.1/ijeat.B10221282S18/18©BEIESP
Open Access | Editorial and Publishing 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: The scope of the project is diagnosis the malignancy of skin disease using digital camera images. Melanoma, a kind of skin disease predominantly distributed amongst 25% of population. If melanoma is detected in its early stage the chances of recovery and medication of diseases are higher. Though dermascopy, a non-invasive skin imaging technique gives a possible solution for accurate screening yet cost of screening is high hence an automated system for diagnosis is required. The image of skin lesion is captured by digital camera using which locating the skin lesion is another challenge of segmenting the vulnerable or affected area from the normal region. To increase the sensitivity and precision of diagnosis skin lesion segmentation algorithm based on texture based is reviewed. Segmentation is performed for accurate detection of lesion and texture distributions are analyzed with illumination corrected image followed by calculating the texture distinctiveness metrics. The prediction of texture distributions in the image can be classified into melanoma or normal skin. The validation of results is done using MATLAB 2017b software.
Keywords: Dermascopy, Skin Lesion Segmentation Algorithm, Texture Distinctiveness.
Scope of the Article: Agent-Based Software Engineering