Loading [MathJax]/extensions/MathMenu.js
Segmenting Cellular Retinal Images by Optimizing Super-Pixels, Multi-Level Modularity, and Cell Boundary Representation | IEEE Journals & Magazine | IEEE Xplore

Segmenting Cellular Retinal Images by Optimizing Super-Pixels, Multi-Level Modularity, and Cell Boundary Representation


Abstract:

We introduce an interactive method for retina layer segmentation in gray-level and RGB images based on super-pixels, multi-level optimization of modularity, and boundary ...Show More

Abstract:

We introduce an interactive method for retina layer segmentation in gray-level and RGB images based on super-pixels, multi-level optimization of modularity, and boundary erosion. Our method produces highly accurate segmentation results and can segment very large images. We have evaluated our method with two datasets of 2D confocal microscopy (CM) images of a mammalian retina. We have obtained average Jaccard index values of 0.948 and 0.942 respectively, confirming the high-quality segmentation performance of our method relative to a known ground truth segmentation. Average processing time was two seconds.
Published in: IEEE Transactions on Image Processing ( Volume: 29)
Page(s): 809 - 818
Date of Publication: 27 August 2019

ISSN Information:

PubMed ID: 31478852

Funding Agency:


I. Introduction

Segmentation is one of the most important tasks in image processing and aims to identify objects of interest in images. In general, objects of interest are defined by some criteria of the underlying application. For example, in medical analysis, objects of interest are usually bones, organs, tissue, cellular structures, or retina layers [1].

References

References is not available for this document.