Performance analysis of knn classifier with and without glcm features in brain tumor detection

Abstract

This paper presents the K-Nearest Neighbour (KNN) classifier combined with Grey Level Co-occurrence Matrix(GLCM) feature extraction technique for brain tumor detection using MATLAB software. Thirty MRI images obtained from the clinical sources are analyzed in this study. Though KNN classifier is less time consuming, it has a disadvantage of less accuracy. To improve the accuracy of KNN classification, GLCM feature extraction is used. Performance of KNN classifier is analyzed with and without GLCM feature extraction.