IMPLEMENTATION OF BRAIN TUMOR IDENTIFICATION USING SVM AND CLASSIFICATION USING BAYESIAN CLASSIFIER IN MRI IMAGES

Abstract

Brain tumors are one of the deadly diseases. Identifying the type of the brain tumor is very essential for the planning of treatment and surgery. Early detection and classification of the tumors will increase the chances of survival. In this paper we propose a methodology for the detection and classification of brain tumors from Magnetic Resonance Imaging (MRI) scans. Here for the tumor detection Support Vector Machine (SVM) is used and for classification of tumor Bayesian classifier is used. MRI segmentation is carried out using Watershed segmentation algorithm. The essential features from MRI are extracted using Zernike Moments.