Abstract:- AdvancedBoost Brain Tumor Classification based on two main components of their system:discrimination and randomization. Discrimination refers to the use of SVM tolearn the splits at each node, whereas randomizased as a form of features tolearn the splits at each node. There are several problems that may arise fromthis randomization procedure. First upon, we considered image patches of size50×50 in a 500×500 images, sampling space may contain thousand of patches,which makes for the images categorization. In this, randomly selected samplesare more likely to over-lap with each other, which would cause redundancy.Therefore in this project, find out new ways for selecting image patchselection should result in higher quality splits at each tree node, which inturn should increase overall accuracy of the classifier.
Keywords: SVM,KNN, RK-RF