Classification of Abnormalities in Brain MRI Images using GLCM, PCA and SVM
Daljit Singh1, Kamaljeet Kaur2
1Daljit Singh, Electronics and Communication Engineering, Ludhiana College of Engineering and Technology, Malerkotla, India.
2Kamaljeet Kaur, Electronics and Communication Engineering, Ludhiana College of Engineering and Technology, Ludhiana, India.
Manuscript received on July 17, 2012. | Revised Manuscript received on August 25, 2012. | Manuscript published on August 30, 2012. | PP: 243-248 | Volume-1 Issue-6, August 2012. | Retrieval Number: F0676081612/2012©BEIESP
Open Access | Ethics and Policies | Cite
© 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: Accurate automatic detection and classification of images is very challenging task whether they are medical images or other natural images. This paper presents a hybrid technique for automatic classification of MRI images as well as natural images. The proposed method consists of two stages: feature extraction and classification. In first stage, features are extracted from images using PCA and GLCM. In the next stage, extracted features are fed as input to SVM classifier. It classifies the images between normal and abnormal along with type of disease depending upon features. Also it classifies between natural images. For Brain MRI images; features extracted with GLCM gives 100% accuracy with SVM -RBF kernel function. Similarly for natural images; features extracted by GLCM gives 91.67% accuracy with SVM-RBF kernel function. Software used is MATLAB R2011a. Main focus is given on Brain MRI images classification as it deals with precious human life.
Keywords: Feature, GLCM, Kernel, MRI, PCA, SVM.