automated recognition of medical images poses a  significant challenge in the field of medical image processing. 
These images are obtained from various modalities such as  Computed Tomography (CT), Magnetic Resonance Imaging 
(MRI), etc., and are crucial for diagnosis purposes. In the medical  field, brain tumor classification is very important phase for the  further treatment. Human interpretation of large number of MRI  slices (Normal or Abnormal) may leads to misclassification hence  there is need of such a automated recognition system, which can  classify the type of the brain tumor. The aim of this study is to  detect brain tumor so we identify various features within an image. 
We extract the feature data from an image Using GLCM , LBP and other filters like Gaussian Filter, Sobel Filter, Laplace Filter,  Gabor Filter, Hessian, Prewitt and create a data frame that can be  fed into binary classification algorithms like Logistic Regression,  KNN and decision tree. The accuracy achieved by Logistic  Regression was 72%, KNN was 65% and decision tree was 80%.