A Comparative Analysis of Depth Computation of Leukaemia Images using a Refined Bit Plane and Uncertainty Based Clustering Techniques

Several image segmentation techniques have been developed over the years to analyze the characteristics of images. Among these, the uncertainty based approaches and their hybrids have been found to be more efficient than the conventional and individual ones. Very recently, a hybrid clustering algorithm, called Rough Intuitionistic Fuzzy C-Means (RIFCM) was proposed by the authors and proved to be more efficient than the conventional and other algorithms applied in this direction, using various datasets. Besides, in order to remove noise from the images, a Refined Bit Plane (RBP) algorithm was introduced by us. In this paper we use a combination of the RBP and RIFCM to propose an approach and apply it to leukemia images. The aim of the paper is twofold. First, it establishes the superiority of our approach in medical diagnosis in comparison to most of the conventional, as well as uncertainty based approaches. The other objective is to provide a computer-aided diagnosis system that will assist the doctors in evaluating medical images in general, and also in easy and better assessment of the disease in leukaemia patients. We have applied several measures like DB-index, D-index, RMSE, PSNR, time estimation in depth computation and histogram analysis to support our conclusions.