Automatic Skin Cancer Images Classification
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2013, Vol 4, Issue 3
Abstract
Early detection of skin cancer has the potential to reduce mortality and morbidity. This paper presents two hybrid techniques for the classification of the skin images to predict it if exists. The proposed hybrid techniques consists of three stages, namely, feature extraction, dimensionality reduction, and classification. In the first stage, we have obtained the features related with images using discrete wavelet transformation. In the second stage, the features of skin images have been reduced using principle component analysis to the more essential features. In the classification stage, two classifiers based on supervised machine learning have been developed. The first classifier based on feed forward back-propagation artificial neural network and the second classifier based on k-nearest neighbor. The classifiers have been used to classify subjects as normal or abnormal skin cancer images. A classification with a success of 95% and 97.5% has been obtained by the two proposed classifiers and respectively. This result shows that the proposed hybrid techniques are robust and effective.
Authors and Affiliations
Mahmoud Elgamal
Keywords
Related Articles
- EP ID EP161702
- DOI 10.14569/IJACSA.2013.040342
- Views 105
- Downloads 0
WE-MQS-VoIP Priority: An enhanced LTE Downlink Scheduler for voice services with the integration of VoIP priority mode
The Long Term Evolution (LTE) is a high data rates and fully All-IP network. It is developed to support well to multimedia services such as Video, VoIP, Gaming, etc. So that, the real-time services such as VoIP, video, e...
Reengineering Framework to Enhance the Performance of Existing Software
Term reengineering refers to improve the quality of the system. Continues maintenance and aging degrade the performance of the software system. Right approach and methodology must be adapted to perform reengineering. Wit...
An Auction-Bidding Protocol for Distributed Bit Allocation in RSSI-based Localization Networks
Several factors (e.g., target energy, sensor density) affect estimation error at a point of interest in sensor networks. One of these factors is the number of allocated bits to sensors that cover the point of interest wh...
Compliance-Driven Architecture for Healthcare Industry
The United States (US) healthcare organizations are continuously struggling to cope-up with evolving regulatory requirements e.g. Health Information Technology for Economic and Clinical Health Act (HITECH) and Internatio...
An Enhanced Concept based Approach for User Centered Health Information Retrieval to Address Presentation Issues
The diversity of health information seekers signifies the enormous variety of information needs by numerous users. The existing health information retrieval systems failed to address the information needs of both medical...