Author:
Li Mingyao,Han Changyuan,Fahim Fadia
Abstract
Skin cancer is one of the most common and dangerous cancers around the world. Early detection of skin cancer can greatly reduce this risk. The main purpose of this paper is to propose an automatic diagnosis system for detecting the healthy and cancerous area. The method includes four
main stages including image contrast enhancement, image segmentation, feature extraction and selection, and images classification. Here, 20 different features are employed and the best of them are selected based on a newly introduced optimization algorithm. In the following, this algorithm
is also applied to a support vector machine for increasing the classification accuracy. The proposed optimization algorithm is a new improved version of the fluid search optimization algorithm based on chaos theory which increases the system convergence speed. The method is compared with four
State of the art methods and shows the superiority of the proposed method toward the analyzed methods.
Publisher
American Scientific Publishers
Subject
Health Informatics,Radiology Nuclear Medicine and imaging
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献