Title: Earth mover's distance-based CBIR using adaptive regularised Kernel fuzzy C-means method of liver cirrhosis histopathological segmentation

Authors: Nirmala S. Guptha; Kiran Kumari Patil

Addresses: Computer Science Engineering, REVA University, Bangalore, Karnataka, India ' Computer Science Engineering, REVA University, Bangalore, Karnataka, India

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.

Keywords: CBIR; content-based image retrieval; EMD; earth mover's distance; FCM; fuzzy C-means; PCA; principal component analysis; ROI; region of interest.

DOI: 10.1504/IJSISE.2017.084568

International Journal of Signal and Imaging Systems Engineering, 2017 Vol.10 No.1/2, pp.39 - 46

Received: 26 Jan 2017
Accepted: 03 Feb 2017
Published online: 14 Jun 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article