TUMOR DETECTION IN MRI IMAGE USING SVM

Abstract

The aim of this work is to present an automated method that assists diagnosis of normal and abnormal MR images. The diagnosis method consists of four stages, pre-processing of MR images, feature extraction, dimensionality reduction and classification. The features are extracted based on discrete wavelet transformation (DWT) using Haar wavelet. We have emphasised on reducing execution time for classification by taking less number of features selected by principal component analysis (PCA) without degrading performance of system so much. In the last stage classification method, Support Vector Machine (SVM) for multi class data is employed. Our work is the modification and extension of the previous studies on the diagnosis of brain diseases, while we obtain better classification rate with the less number of features and we have used larger and rather different database to classify tumors in different classes on the basis of location in different parts of brain.