Comparative Study of Kernel SVM and ANN Classifiers for Brain Neoplasm Classification

In this article an efficient classification method is proposed for classifying brain neoplasm detected in Magnetic Resonance Imaging (MRI) images. For training purpose 13 features are extracted from the Gray Level Co-occurrence Matrix (GLCM) of MRI images. Also classification accuracy is assessed via 10-fold rotation estimation scheme. In present work two classifiers Support Vector Machine (SVM) and Artificial Neural Network (ANN) have been compared using accuracy, performance measure MSE and computational time requirement. A prominent accuracy has been attained in case of multilayer ANN for a given dataset.