Aswin.R.B et al, International Journal of Computer Science and Mobile Computing, ICMIC13, December- 2013, pg. 87-94 © 2013, IJCSMC All Rights Reserved 87 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X International Conference on Mobility in Computing- ICMiC13, Organized by Mar Baselios College of Engineering and Technology during December 17-18, 2013 at Trivandrum, Kerala, India, pg.87 – 94 SURVEY ARTICLE Implementation of ANN Classifier using MATLAB for Skin Cancer Detection Aswin.R.B 1 , J. Abdul Jaleel 2 , Sibi Salim 3 1 Dept. of Electrical & Electronic Engineering, Mar Baselios College of Engineering and Technology, Kerala, India 2,3 Dept. of Electrical & Electronic Engineering, TKM College of Engineering, Kollam, India aswinrb@gmail.com 1 , drjaleel56@gmail.com 2 , sibi_salim@rediffmail.com 3 Abstract — Skin cancer is the deadliest form of cancers in humans. Skin cancer is commonly known as Melanoma. Melanoma is named after the cell from which it presumably arises, the melanocyte. Skin Cancers are of two types- Benign and Malignant Melanoma. Melanoma can be cured completely if it is detected early. Both benign and malignant melanoma resembles similar in appearance at the initial stages. So it is difficult to differentiate both. This is a main problem with the early skin cancer detection. Only an expert dermatologist can classify which one is benign and which one is malignant. The Artificial Neural Network based Classification methodology uses Image processing techniques and Artificial Intelligence for early diagnosis. Main advantage of this computer based classification is that patient does not need to go to hospitals and undergo various painful diagnosing techniques like Biopsy. In this Computer Aided Classification, dermoscopy image of skin cancer is taken and it is subjected to various pre-processing and image enhancement. The cancer affected region is separated from the healthy skin using Segmentation. In order to reduce the complexity of classification, some unique features of malignant and benign melanoma are extracted. 2DWavelet transform is the Feature Extraction Method used. These features are given as the input to the Artificial Neural Network Classifier. It classifies the given data set into cancerous or non-cancerous. Keywords— Melanoma; Biopsy; Segmentation; 2DWavelet transform; Artificial Neural Network I. INTRODUCTION Skin is the outermost covering of human body. It is a protective layer of the body which acts as first line of defense against foreign particles entering into the body. There are many diseases or conditions that affect the skin, one such abnormality occurring in skin is skin cancer. Normal cells grow in a controlled way such that new cells replace the old ones. But in the case of cancer, they grow in an abnormal way. Normal cells become cancerous due to the genetic disorders occurring in the nucleus of the cells by external or internal factors Skin cancer at its early stages can be cured. But when it is not recognized at its early stages, it begins to spread to other parts of the body and can be deadly.