Identification of Abnormality from Endoscopic Color Images Using Normalized Cuts
Ravindra S. Hegadi · International Conference on Intelligent Information Processing · 2010
The normalized cut criterion measures both the total dissimilarity between the different groups as well as the total similarity within the groups. These methods perform segmentation of the images through hierarchical partitioning instead of performing single flat partition. In this paper the normalized cuts method of segmentation is used to perform the segmentation of abnormal region from endoscopic images. The other image features such as image brightness, color and texture are considered while performing segmentation. The experimentation is carried out on 50 images containing tumor. The results of segmentation of tumor from the endoscopic images using the proposed method are very encouraging.