Title :
Classification of magnetic resonance images
Author :
Trojacanec, Katarina ; Madzarov, Gjorgji ; Gjorgjevikj, Dejan ; Loskovska, Suzana
Author_Institution :
Fac. of Electr. Eng. & Inf. Technol., Ruger Boskovik bb., Skopje, Macedonia
Abstract :
The aim of the paper is to compare classification error of the classifiers applied to magnetic resonance images for each descriptor used for feature extraction. We compared several Support Vector Machine (SVM) techniques, neural networks and k nearest neighbor classifier for classification of Magnetic Resonance Images (MRIs). Different descriptors are applied to provide feature extraction from the images. The dataset used for classification contains magnetic resonance images classified in 9 classes.
Keywords :
feature extraction; image classification; magnetic resonance imaging; neural nets; support vector machines; MRI; feature extraction; image classification; k nearest neighbor classifier; magnetic resonance image; neural networks; support vector machine; Artificial neural networks; Classification algorithms; Feature extraction; Histograms; Magnetic resonance; Magnetic resonance imaging; Support vector machines; Classification; Magnetic Resonance Images (MRIs); Support Vector Machines (SVMs); neural networks;
Conference_Titel :
Information Technology Interfaces (ITI), 2010 32nd International Conference on
Conference_Location :
Cavtat/Dubrovnik
Print_ISBN :
978-1-4244-5732-8
