Support Vector Machine for MRI Stroke Classfication
Journal Title: International Journal on Computer Science and Engineering - Year 2014, Vol 6, Issue 4
Abstract
Magnetic resonance imaging (MRI) is a low-risk, non-invasive imaging technique without ionizing radiation hazard, providing high quality/high contrast images and functional images of anatomical structures and organs. In this study, a method to classify the MRI images of the brain related to stroke is presented. Stroke is a sudden development of neurological damage. In this paper, the MRI images for stroke classification use Gabor filters and Histograms to extract features from the images. In the proposed feature extraction method, the features from Gabor filter and histogram features are fused. The extracted features are classified using Support Vector Machine (SVM) with various kernels. Experimental results are shown that the presented method achieves satisfactory classification accuracy
Authors and Affiliations
A. S. Shanthi , M. Karthikeyan
Keywords
Related Articles
- EP ID EP126680
- DOI -
- Views 123
- Downloads 0
Solving Sparse Rating Problem Using Fine Grained Approach
Recommender System is a system that automatically recommends all similar kind of items that are of user interest. In design of the recommender systems rating is the crucial issue. Till today many algorithms have been pro...
Effect of Modulation Schemes on Performance of OFDM based Wireless Network using Smart Antenna
In this paper we have presented the effect of different modulation Techniques (QPSK, 16QAM and 64QAM) and number of antenna elements at the receiver (Smart Antenna) on the performance of beamforming in OFDM based Wireles...
DESIGN & MODELING OF MANET USING DIFFERENT SLOT TIME SIMULATED BY NS-2
IEEE 802.11 MAC protocol has been the standard for Wireless LANs, and also adopted in many network simulation packages for wireless multi-hop ad hoc networks.MAC is defined to proper access to the channel and that is als...
Study of Efficient Technique Based On 2D Tsallis Entropy For Image Thresholding
Thresholding is an important task in image processing. It is a main tool in pattern recognition, image segmentation, edge detection and scene analysis. In this paper, we present a new thresholding technique based on two-...
IRIS RECOGNITION BASED ON GAUSSIAN-HERMITE MOMENTS
Iris recognition is accepted as one of the most efficient biometric method. Implementing this method to the practical system requires the special image preprocessing where the iris feature extraction plays a crucial role...