GLCM – SVM based Classification of Brain MRI with K-Means Clusters
B.Thamaraichelvi
B.Thamaraichelvi*, Department of Electrical Engineering, Annamalai University,Chidambaram,Tamil Nadu, India.
Manuscript received on February 01, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 100-104 | Volume-9 Issue-3, February, 2020. | Retrieval Number: B4500129219/2020©BEIESP | DOI: 10.35940/ijeat.B4500.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this proposed method, MR Brain image segmentation technique based on K-means clustering combined with Discrete Wavelet Transform (DWT) based feature extraction and Gray Level Co-Occurrence Matrix (GLCM) based feature selection approach has been presented. A Perfect Radial Basis Function (RBF) – Support Vector Machine (SVM) Classifier has been selected for this process. The Performance of the classifier was estimated through accuracy based on the fractions selectivity and sensitivity. Accuracy of the proposed classifier was found to be 93%. Moreover, in this proposed method, instead of selecting the cluster centres in a random manner, Histogram technique was used.
Keywords: Centroid selection, Discrete Wavelet Transforn (DWT), GLCM feature selection, Histon formation, K-means clustering, RBF-SVM Classifier.