Earth mover's distance-based CBIR using adaptive regularised Kernel fuzzy C-means method of liver cirrhosis histopathological segmentation
by Nirmala S. Guptha; Kiran Kumari Patil
International Journal of Signal and Imaging Systems Engineering (IJSISE), Vol. 10, No. 1/2, 2017

Abstract: Liver cirrhosis is the most common disease, which caused many serious problems in adults and also old people. Much advancement has been arrived in the treatment and diagnosis of cirrhosis, still identifying the exact affected region is a challenging one. Content-based image retrieval in the identification of liver cirrhosis is a popular task performed usually, in which many techniques are introduced by the researchers so far. This paper is a part among all, which focus on providing the efficient detection of cirrhosis on the basis of separation and location of nuclei method. The liver cells are classified, and the overlapping of nuclei and non-nuclei cells is separated to evaluate the distance among them so as to locate the disease. The classification of cells is implemented with the help of adaptive regularised Kernel fuzzy C-means technique, and the distance between consecutive nuclei and non-nuclei is estimated by using earth movers distance. The experimental results and their analysis describe that the proposed method performs well than the other methods.

Online publication date: Wed, 14-Jun-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Signal and Imaging Systems Engineering (IJSISE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com