Algorithm 2: The proposed SVM classifier technique

Inputs: Training and testing images. Outputs: Calculated accuracy. Select the optimal value of cost and gamma for SVM. While (stopping condition is not met) Do Step 1: Implement the SVM train step for each data point. Step 2: Implement SVM classification for testing data points. Step 3: Define SVM-based kernel as $k\left(x,y\right)=exp exp (\frac{\Vert x-y\Vert }{\sigma })$. Where x, y belong to the samples of feature space in the training set parameter. Step 4: The objective is to have four classes:       1- Normal (Not Tumour)       2- Tumour, with three subclasses: 1.Glioma. 2.Meningioma. 3.Pituitary. End While Return accuracy