Segmentation of Magnetic Resonance Imaging MRI using LS-SVM and Wavelet Multiresolution Analysis
Keywords:
Kernel, LS-SVM, optimization, segmentation, mother wavelet
Abstract
Currently, support vector machines (SVM) have become a powerful tool to solve nonlinear classification problems. For the optimization of the tool, has developed a reformulation known as LS-SVM (Support Vector Machine least squares), which works with a model based on function minimization and Lagrange polynomials. Therefore, this paper presents a method for segmentation of magnetic resonance images specifically to study the morphology of the lungs and reach the quantification of relevant features in these images using SVM and LS-SVM. In addition to sorting technique in this work using techniques such as wavelet analysis to eliminate irrelevant information (compression) and Splines algorithms to interpolate the information found and quantify the characteristics, which in this work were based on the recognition area, shape and abnormal structures present in the lung of these images.
How to Cite
[1]
L. A. Muñoz-Bedoya, L. E. Mendoza, and H. J. Velandia-Villamizar, “Segmentation of Magnetic Resonance Imaging MRI using LS-SVM and Wavelet Multiresolution Analysis”, TecnoL., pp. 681–693, Nov. 2013.
Downloads
Download data is not yet available.
Published
2013-11-19
Issue
Section
Computer science