Please use this identifier to cite or link to this item: http://localhost:8081/xmlui/handle/123456789/11495
Title: SEGMENTATION OF LIVER IMAGES
Authors: Karthik, Kusupati Vijaya
Keywords: ELECTRICAL ENGINEERING;SEGMENTATION;LIVER IMAGES;IMAGE SEGMENTATION
Issue Date: 2010
Abstract: Image segmentation plays a crucial role in many medical imaging applications by facilitating the delineation of anatomical structures and other regions of interest. Segmentation is the process of dividing images into constituent sub regions. Manual segmentation is possible but is a time-consuming task and subject to operator variability. Various techniques available for medical image segmentation are discussed briefly. Among those clustering techniques k-means clustering method and FCM are dealt in detail. K-means is one of the simplest unsupervised clustering algorithms, which has been widely used in various applications. Where as FCM is frequently used in pattern recognition. In this technique, data points are bound to each cluster by means of membership functions, which give degree of association to the cluster. k-means and FCM method are applied to liver images in order to get the clusters and analyze the liver images. Their performance is evaluated using Global silhouette value which when approaches to unity suggests that the method is superior to other. In simple words if silhouette value tends to unity the method which is used is better than the other method. Ultrasound liver images are taken extensively and their analysis using K-means clustering technique and FCM clustering technique is made in detail.
URI: http://hdl.handle.net/123456789/11495
Other Identifiers: M.Tech
Research Supervisor/ Guide: Anand, R. S.
metadata.dc.type: M.Tech Dessertation
Appears in Collections:MASTERS' THESES (Electrical Engg)

Files in This Item:
File Description SizeFormat 
EEDG20410.pdf3.56 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.