Investigation of Abnormal Skin Lesion Analysis System for Melanoma Early Detection Using Image Processing
Keywords:K-Means, Fuzzy-C, Chan Vese, ROI (Region Of Interest), accuracy, sensitivity, precision, F measure Ada boost, GLCM( gray-level co-occurrence matrix) Melanoma, Lesion.
In this paper, acquisition of lesion image is carried out and compared using three different segmentation algorithm. Otsuâ€™s method based thresholding technique is used to minimize variance of the background and foreground pixels. Here tone detection and exclusion, three ROI segmentation models (K-means, Fuzzy-C means, Chan Vese model) followed by hybrid feature extraction, and classification methods are carried out. Accuracy, sensitivity, precision , F measure of the acquired lesion image are obtained by using the above segmentation methods and the best method is examined.
 S. Suer, S. Kockara, and M. Mete, â€˜â€˜An improved border detection in dermoscopy images for density based clustering,â€™â€™ BMC Bioinformat., vol. 12, no. 10, p. S12, 2011.
 M. Rademaker and A. Oakley, â€˜â€˜Digital monitoring by whole body photography and sequential digital dermoscopy detects thinner melanomas,â€™â€™ J. Primary Health Care, vol. 2, no. 4, pp. 268â€“272, 2010.
 O. Abuzaghleh, B. D. Barkana, and M. Faezipour, â€˜â€˜SKINcure: A real time image analysis system to aid in the malignant melanoma prevention and early detection,â€™â€™ in Proc. IEEE Southwest Symp. Image Anal. Interpretation (SSIAI), Apr. 2014, pp. 85â€“88.
 O.Abuzaghleh, B.D.Barkana, and M.Faezipour,â€˜â€˜ Automated skin lesion analysisbasedoncolo rand shape geometry feature set form elanoma early detection and prevention,â€™â€™inProc.IEEELongIslandSyst.,Appl.Technol. Conf. (LISAT), May 2014, pp. 1â€“6.
 (Mar. 27, 2014). American Cancer Society, Cancer Facts & Figures. [Online]. Available: http://www.cancer.org/research/cancerfactsstatistics/ cancerfactsï¬gures2014/index
 R. P. Braun, H. Rabinovitz, J. E. Tzu, and A. A. Marghoob, â€˜â€˜Dermoscopy researchâ€”An update,â€™â€™ Seminars Cutaneous Med. Surgery, vol. 28, no. 3, pp. 165â€“171, 2009.
 Dr. AntoBennet, M, Sankar Babu G, Natarajan S, â€œReverse Room Techniques for Irreversible Data Hidingâ€, Journal of Chemical and Pharmaceutical Sciences 08(03): 469-475, September 2015.
 Dr. AntoBennet, M , Sankaranarayanan S, Sankar Babu G, â€œ Performance & Analysis of Effective Iris Recognition System Using Independent Component Analysisâ€, Journal of Chemical and Pharmaceutical Sciences 08(03): 571-576, August 2015.
 Dr. AntoBennet, M, Suresh R, Mohamed Sulaiman S, â€œPerformance &analysis of automated removal of head movement artifacts in EEG using brain computer interfaceâ€, Journal of Chemical and Pharmaceutical Research 07(08): 291-299, August 2015.
 .Dr. AntoBennet, M â€œA Novel Effective Refined Histogram For Supervised Texure Classificationâ€, International Journal of Computer & Modern Technology , Issue 01 ,Volume02 ,pp 67-73, June 2015.
 Dr. AntoBennet, M, Srinath R,Raisha Banu A,â€œDevelopment of Deblocking Architectures for block artifact reduction in videosâ€, International Journal of Applied Engineering Research,Volume 10, Number 09 (2015) pp. 6985-6991, April 2015.
 AntoBennet, M & JacobRaglend, â€œPerformance Analysis Of Filtering Schedule Using Deblocking Filter For The Reduction Of Block Artifacts From MPEQ Compressed Document Imagesâ€, Journal of Computer Science, vol. 8, no. 9, pp. 1447-1454, 2012.
 AntoBennet, M & JacobRaglend, â€œPerformance Analysis of Block Artifact Reduction Scheme Using Pseudo Random Noise Mask Filteringâ€, European Journal of Scientific Research, vol. 66 no.1, pp.120-129, 2011.