A STUDY ON CLASSIFICATION TECHNIQUES FOR THE IDENTIFICATION OF TUMOR TYPES IN ABNORMAL BRAIN MR IMAGES

Authors

  • Sree Sankar. J R. A. Isabel, Bipin Dev S.S Author

Keywords:

Self-Organizing Map, Artificial Neural Networks, Support Vector Machine, Zernike moments

Abstract

The tumor detection and classification over the Magnetic Resonance Images is a systematic procedure. The correct identification of the type of brain tumor is essential for the further treatments and surgical planning in future.The usage of the advanced techniques is very essential for the proper identification of the type of the tumor without any kind of faults. In order to satisfy this requirement here two well-known classification techniques such as Artificial Neural Networks (ANN) and Self-Organizing Map (SOM) are used. Zernike moments are used for feature extraction and MRI segmentation is carried out by using Expectation-Maximization algorithm. Here for the identification of the abnormalities in the MRI images Support Vector Machine (SVM) is used. The types of tumors are identified individually using the two classifiers from a set of brain tumor images and finally the time complexities for the two are analyzed.

Downloads

Published

2016-06-12

Issue

Section

Articles

How to Cite

A STUDY ON CLASSIFICATION TECHNIQUES FOR THE IDENTIFICATION OF TUMOR TYPES IN ABNORMAL BRAIN MR IMAGES. (2016). Global Journal of Advanced Engineering Technologies and Sciences, 3(6), 31-36. https://gjaets.com/index.php/gjaets/article/view/212

Most read articles by the same author(s)

1 2 3 4 5 6 7 8 9 10 > >>