Discriminant method for severity of glandular tumor by support vector machine

In this study, glandular tumor images are classified automatically by the support vector machine (SVM) in order to make up for a fault of discriminant analysis, Mahalanobispsila generalized distance which was used in recent studies. The fault of Mahalanobispsila generalized distance is the problem, that is to say, the Curse of Dimensionality. To avoid this problem, we used the support vector machine (SVM) as the discriminant analysis, used the prostate images as glandular tumor images, and examined the effectiveness of this system.