National Conference on Recent Trends in Computing |
Foundation of Computer Science USA |
NCRTC - Number 2 |
May 2012 |
Authors: Basavaraj A Goudannavar, Ravindra S. Hegadi, Neelangouda Patil |
ee06d766-9469-4e07-9a19-3db89a1e6a0d |
Basavaraj A Goudannavar, Ravindra S. Hegadi, Neelangouda Patil . Humerus Radiograph Image Segmentation using Normalized Cut. National Conference on Recent Trends in Computing. NCRTC, 2 (May 2012), 22-24.
Image segmentation techniques have been widely applied in diagnosis systems with medical image support. In this paper we propose the normalized cuts method for image segmentation problem, which is based on Graph Theory. These algorithms treat an image pixel as a node of graph, and consider segmentation as a graph partitioning problem. The Normalized Cuts algorithm measures both the total dissimilarity between the different groups as well as the total similarity within the groups. The pixel value of gray scale and color Images are considered for clustering dissimilarity and similarity group. The optimal solution of splitting points is easily computed by solving a generalized eigenvalue problem. The results of the proposed method are encouraging.