This paper presents a new technique of segmentation and feature extraction for classification of melanoma and non-melanoma. Both segmentation and feature extraction is done by the concept of average value since average is the number closer to every number. Here we have also compared K-means segmentation technique with new the technique. In experimental part we evaluate 80.897% average accuracy through neural network classification.

Segmentation, Global + Local Segmentation, Center Starting Feature Extraction, K-means Segmentation, Feature Extraction

[1] S. Ramteke Nilkamal and V. Jain Shweta, “Analysis of Skin Cancer Using Fuzzy and Wavelet Technique-Review and Proposed New Algorithm”, International Journal of Engineering Trends and Technology, volume 4, issue 6, june 2013.
[2] Melanoma Early Detection and Treatment could save your life, Melanoma Institute of Australia, https://www.melanoma.org.au
[3] Sujaya Saha, Rajat Gupta, An Automatic Skin Lesion Diagnosis by using Image Processing Techniques, International Journal on Recent and Innovation Trends in Computing and Communication, Volume2, Issue 5, May 2014.
[4] J.Abdul Jaleel, Sibi Salim, R.B. Aswin, Artifical Neural Network Based Detection of Skin Cancer, International Journal of Advanced Research in Electrical, Electronic and Instrumental Enggineering, vol. 1, Issue 3, September 2012.
[5] M. Messadi, A. Bessaid and A. Taleb Ahmed, Extraction of specific parameter for skin tumor classification, Journal of Medical Engineering and Technology, vol. 33, no. 4, May 2009, 288-295.
[6] Sonali Raghunath Jadhav, D.K. Kamat, Segmentation Based Detection of Skin Cancer, Proceedings of 13th IRF International Conference, 20th July 2014, Pune, India, ISBN: 978-93-84209-37-7.
[7] J. Premaladha, S. Sujitha, M. Lakshmi Priya and K.S. Ravichandra, A Survey on Melanoma Diagnosis using Image Processing and Soft Computing Technique, Research Journal of Information Technology, 6. 65-80, May 20, 2014.
[8] Priyadarshni D, Rengini D, Automatic Melanoma Detection Using Local Binary Pattern and Support Vector Machine, International Journal of Innovative Research in Computer and Communication Engineering, vol. 3, issue 9, September 2015.
[9] Stanley, R. Joe, Randy Hays Moss and Chetna Aggarwal. "A fuzzy based hostogram analysis technique for skin lesion descrimination in dermatology clinical images", Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society, Vol. 27, No. 5, pp. 387-396, 2003.
[10] Ercal, Fikret, et al. "Neural network diagnosis of malignant melanoma from color images", IEEE Transactions on Biolmedical Engineering, Vol.41, No. 9, pp. 837-845, 1994.
[11] Rashi Goel and Saranjeet Singh, “Skin Cancer Detection Using GLCM Matrix Analysis And SVM Classifier ”, International Journal of Applied Engineering and Technology ISSN:2272-212X, 2015 vol. 5.
[12] Antonio Fernandez, Marcos X. Alvarez Francesco Bianconi, “Texture Description Through Histograms of Equivalent Patterns”, 12 September 2012, Springer Science+Business Media, LLC 2012
[13] Nanni, L., Brahnam, S., Lumini, A.: Survey on LBP based texture descriptors for image classification. Expert Syst. Appl.39(3), 3634–3641 (2012).
[14] Huang, D., Shan, C., Ardabilian, M., Wang, Y., Chen, L.: Local binary patterns and its application to facial image analysis: a survey, IEEE Trans. Syst. Man Cybern., Part C, Appl. Rev. 41(6), 765–781 (2011)
[15] S.Sridhar, Digital Image Processing, 2nd ed. New Delhi: Oxford University Press.