Detection and classification of brain tumor in MRI images using wavelet transform and support vector machine

Authors:
Publisher website
Google Scholar
Abstract
A Tumor infected brain is well thought-out as a fearsome disease. It is a spot that surfaces in the human brain from some irregular growth of the cell. The recognition and categorization of such an infected brain part through the MR imaging technique is a wearisome and stretched job. However, with a variety of techniques of Imaging, the sundry structure of the human brain can be visualized. Nevertheless, it is intricate to sense strange brain compositions with usual image processing techniques. MRI distinguishes and clarifies the neural design of the human brain. This paper put forward an analytical course of action for the recognition of brain tumors (BT). It focuses on the eradication of noise, features extraction based on gray-level co-occurrence matrix (GLCM) and BT segmentation based on Discrete Wavelet Transform (DWT) in order to augment the performance and shrivel the complexity. Morphological operation is performed to eradicate the noise that emerged due to segmentation. Support Vector Machine (SVM) based classifier is used to access the accuracy of BT detection. Experimental results exhibit a classification accuracy of 98.91% that shows the proposed system efficacy.

This publication has 9 references indexed in Scilit: