Hybrid retinal image registration using mutual information and salient features

Jaeyong Ju, Murray Loew, Bonhwa Ku, Hanseok Ko

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a method for registering retinal images. Retinal image registration is crucial for the diagnoses and treatments of various eye conditions and diseases such as myopia and diabetic retinopathy. Retinal image registration is challenging because the images have non-uniform contrasts and intensity distributions, as well as having large homogeneous non-vascular regions. This paper provides a new retinal image registration method by effectively combining expectation maximization principal component analysis based mutual information (EMPCA-MI) with salient features. Experimental results show that our method is more efficient and robust than the conventional EMPCA-MI method.

Original languageEnglish
Pages (from-to)1729-1732
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE99D
Issue number6
DOIs
Publication statusPublished - 2016 Jun 1

Fingerprint

Image registration
Principal component analysis

Keywords

  • Medical Imaging
  • Mutual Information
  • Retinal Image Registration
  • Salient Features

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Hybrid retinal image registration using mutual information and salient features. / Ju, Jaeyong; Loew, Murray; Ku, Bonhwa; Ko, Hanseok.

In: IEICE Transactions on Information and Systems, Vol. E99D, No. 6, 01.06.2016, p. 1729-1732.

Research output: Contribution to journalArticle

@article{815e3056c9fb44e28dc704997ab3d181,
title = "Hybrid retinal image registration using mutual information and salient features",
abstract = "This paper presents a method for registering retinal images. Retinal image registration is crucial for the diagnoses and treatments of various eye conditions and diseases such as myopia and diabetic retinopathy. Retinal image registration is challenging because the images have non-uniform contrasts and intensity distributions, as well as having large homogeneous non-vascular regions. This paper provides a new retinal image registration method by effectively combining expectation maximization principal component analysis based mutual information (EMPCA-MI) with salient features. Experimental results show that our method is more efficient and robust than the conventional EMPCA-MI method.",
keywords = "Medical Imaging, Mutual Information, Retinal Image Registration, Salient Features",
author = "Jaeyong Ju and Murray Loew and Bonhwa Ku and Hanseok Ko",
year = "2016",
month = "6",
day = "1",
doi = "10.1587/transinf.2015EDL8265",
language = "English",
volume = "E99D",
pages = "1729--1732",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "6",

}

TY - JOUR

T1 - Hybrid retinal image registration using mutual information and salient features

AU - Ju, Jaeyong

AU - Loew, Murray

AU - Ku, Bonhwa

AU - Ko, Hanseok

PY - 2016/6/1

Y1 - 2016/6/1

N2 - This paper presents a method for registering retinal images. Retinal image registration is crucial for the diagnoses and treatments of various eye conditions and diseases such as myopia and diabetic retinopathy. Retinal image registration is challenging because the images have non-uniform contrasts and intensity distributions, as well as having large homogeneous non-vascular regions. This paper provides a new retinal image registration method by effectively combining expectation maximization principal component analysis based mutual information (EMPCA-MI) with salient features. Experimental results show that our method is more efficient and robust than the conventional EMPCA-MI method.

AB - This paper presents a method for registering retinal images. Retinal image registration is crucial for the diagnoses and treatments of various eye conditions and diseases such as myopia and diabetic retinopathy. Retinal image registration is challenging because the images have non-uniform contrasts and intensity distributions, as well as having large homogeneous non-vascular regions. This paper provides a new retinal image registration method by effectively combining expectation maximization principal component analysis based mutual information (EMPCA-MI) with salient features. Experimental results show that our method is more efficient and robust than the conventional EMPCA-MI method.

KW - Medical Imaging

KW - Mutual Information

KW - Retinal Image Registration

KW - Salient Features

UR - http://www.scopus.com/inward/record.url?scp=85009075021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009075021&partnerID=8YFLogxK

U2 - 10.1587/transinf.2015EDL8265

DO - 10.1587/transinf.2015EDL8265

M3 - Article

AN - SCOPUS:85009075021

VL - E99D

SP - 1729

EP - 1732

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 6

ER -