Lumbar Spine Image Segmentation using Linked Outlyingness Tree
B. Suresh Kumar

B. Suresh Kumar, Assistant Professor, Department of Computer Science, SAN International College of Arts and Science, Coimbatore (Tamil Nadu), India.

Manuscript received on 02 November 2017 | Revised Manuscript received on 21 November 2017 | Manuscript Published on 30 December 2017 | PP: 1-7 | Volume-7 Issue-2, November 2017 | Retrieval Number: B2472117217/2017©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Image segmentation is the process of partitioning a digital image into multiple segments. The purpose of image segmentation is to partition an image into meaningful regions with respect to a particular application. The image segmentation is used for various applications such as medical images, satellite images, content based image retrieval, machine vision, recognition tasks and video surveillance etc. Many methods such as compression based methods, thresholding, and clustering has been proposed in literature for segmentations. The clustering methods can be divided into two parts, namely supervised and unsupervised. Supervised clustering involves predefining the cluster size for segmenting whereas unsupervised image segmentation segments by its own cluster values. The spine segmentation method validates cluster extraction and subsequently vertebral image is obtained. The previous methods for segmenting images in the medical field are taking more time and less accuracy of vertebral outputs. In order to overcome the disadvantages a new methodologies proposed. In this proposed work three methods have been implemented, namely lumbar spine image Segmentation using linked outlyingness tree. Supervised image segmentation using LOT, Unsupervised. Comparing each other Lumbar spine image segmentation provides the best solution for medical images. The performance results also proved that the proposed system has better performance over other existing algorithms.
Keyword: Computed Tomography (CT), Magnetic Resonance Image (MRI), Linked Outlyingness Tree (LOT), Robust Outlyingness Ratio (ROR).
Scope of the Article: Robotics