Modeling sets of unordered points using highly eccentric ellipses

Demetrios Gerogiannis,Aristidis Likas,Christophoros Nikou

doi:10.1186/1687-6180-2014-11

Demetrios Gerogiannis, Aristidis Likas + Show 1 more

Open Access

https://doi.org/10.1186/1687-6180-2014-11

Copy DOI

Abstract

An algorithm for modeling a set of unordered two-dimensional points by line segments is presented. The points are modeled by highly eccentric ellipses, and line segments are extracted by the major axes of these elongated ellipses. At first, a single ellipse is fitted to points which is then iteratively split to a large number of highly eccentric ellipses to cover the set of points. Then, a merge process follows in order to combine neighboring ellipses with almost collinear major axes to reduce the complexity of the model. Experimental results on various databases show that the proposed scheme is an efficient technique for modeling unordered sets of points and shapes by line segments. A computer vision application of the method is also presented regarding the detection of retinal fundus image features, such as end-points, junctions, and crossovers.

Highlights

1 Introduction In many computer vision applications, at a mid-level process, it is common to fit line segments in order to model a set of unordered points so as to summarize higher level features
The Hough transform (HT) is a widely used method for line fitting, and many variants have been proposed to improve its efficiency [6,7]. One of these variants is the randomized Hough transform (RHT) [8,9] which randomly selects a number of pixels from the input image and maps them into one point in the parameter space which was shown to be less complex, compared to the original algorithm, as far as time and
We propose a method to model a set of unordered points by line segments

Summary

Introduction

In many computer vision applications, at a mid-level process, it is common to fit line segments in order to model a set of unordered points so as to summarize higher level features. The Hough transform (HT) is a widely used method for line fitting, and many variants have been proposed to improve its efficiency [6,7]. One of these variants is the randomized Hough transform (RHT) [8,9] which randomly selects a number of pixels from the input image and maps them into one point in the parameter space which was shown to be less complex, compared to the original algorithm, as far as time and

Methods

Results

Conclusion