International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 53 - Number 11 |
Year of Publication: 2012 |
Authors: Yogendra Kumar Jain, Megha Jain |
10.5120/8465-2386 |
Yogendra Kumar Jain, Megha Jain . Comparison between Different Classification Methods with Application to Skin Cancer. International Journal of Computer Applications. 53, 11 ( September 2012), 18-24. DOI=10.5120/8465-2386
In recent years, skin cancer is the most common form of human cancer. It is estimated that over 1 million new cases occur annually. In order to detect skin cancer various methods have been proposed in the past decades. This paper focuses on the development of a skin cancer screening system that can be used in a general practice by non-experts to classify normal from abnormal cases. The development process consists of Feature Detection and Classification Technique. The features are extracted by decomposing images into different frequency sub-bands using wavelet transform. The output of Discrete Wavelet Transform becomes input to the Classification System which classify whether the input image is cancerous or noncancerous. The classification system is based on the application of Probabilistic Neural Network and Clustering Classifier. The Accuracy of the proposed system is calculated using different classification techniques on image database of 80 samples (40 cancerous and 40 non cancerous images).