New medical image classify approach based on improved SVM classifier
Zhanhuai Li · Jisuanji yingyong yanjiu · 2008
Support vector machine(SVM) has high classify accuracy and good capabilities of fault-tolerance and generalization.The rough sets theory approach has the advantages on dealing with great data and eliminating redundant information.This paper joined the SVM classifier with rough sets theory which called the improved SVM(ISVM) to classify digital mammography.The experimental results show that the improved SVM classifier can get 96.56% accuracy which is higher about 3.42% than 92.94% using SVM,and the error recognition rates are closed to 100% averagely.