Segmentation of Brain MRI Images using Fuzzy c-means and DWT

Author(s):

Pooja B Minajagi , Visvesvaraya Technological University, Belagavi; R H Goudar, Visvesvaraya Technological University, Belagavi

Keywords:

Fuzzy c means clustering, SFCM, PCA, DWT

Abstract:

Medical image processing deals with enhancement, segmentation etc. of medical images like brain MRI, CT scan images of liver, pancreas etc. The segmentation of the part in image is to be done accurately. Especially in medical images, the segmentation result has to be accurate. In this proposed work, the brain MRI images segmentation using fuzzy c means clustering (FCM) and discrete wavelet transform (DWT). In this work, two algorithms are considered. One is level set segmentation using fuzzy c means by using special features (SFCM) and another one is segmentation of brain MRI images using DWT and principal component analysis (PCA) are further processed using support vector machine (SVM) for classification. The performance evaluation is done by computing mean square error, peak signal to noise ratio (PSNR), maximum difference, absolute mean error etc. Here DWT uses k- means clustering and level set uses fuzzy c- means clustering. The spatial constraints are named with different indexes such as the user can choose on particular region of interest and iterate the contour steps until more accurate result to be obtained.

Other Details:

Manuscript Id	:	IJSTEV2I12162
Published in	:	Volume : 2, Issue : 12
Publication Date	:	01/07/2016
Page(s)	:	370-378

Download Article