Publication detail

Hybrid retinal image registration using phase correlation

KOLÁŘ, R. HARABIŠ, V. ODSTRČILÍK, J.

Original Title

Hybrid retinal image registration using phase correlation

English Title

Hybrid retinal image registration using phase correlation

Type

journal article - other

Language

en

Original Abstract

This paper deals with registration of retinal images, which were taken by highresolution digital colour fundus cameras. The proposed method describes successful application of phase correlation method. It combines several basic steps - global correction of shift, rotation and scaling, detection of landmarks, their correspondences and finally image registration using second-order polynomial model. The method is tested on two sets of images. The first set contains images from the diabetic patients where many retinal pathologies can disturb the registration process. The second set contains images from healthy subjects, which were acquired by different illumination conditions. The method was evaluated using four different criteria - tree objective and one subjective. These criteria are also compared. The achieved registration accuracy of the landmarks position error is 1.13 and 0.93 pixels for respective image sets. Finally, the simple scheme for retinal pathology visualisation of registered fundus pairs is presented.

English abstract

This paper deals with registration of retinal images, which were taken by highresolution digital colour fundus cameras. The proposed method describes successful application of phase correlation method. It combines several basic steps - global correction of shift, rotation and scaling, detection of landmarks, their correspondences and finally image registration using second-order polynomial model. The method is tested on two sets of images. The first set contains images from the diabetic patients where many retinal pathologies can disturb the registration process. The second set contains images from healthy subjects, which were acquired by different illumination conditions. The method was evaluated using four different criteria - tree objective and one subjective. These criteria are also compared. The achieved registration accuracy of the landmarks position error is 1.13 and 0.93 pixels for respective image sets. Finally, the simple scheme for retinal pathology visualisation of registered fundus pairs is presented.

Keywords

retinal imaging, image registration, phase correlation, feature extraction, segmentation, visualisation

RIV year

2013

Released

01.05.2013

Publisher

Maney Publishing

Location

London, UK

Pages from

269

Pages to

384

Pages count

16

URL

BibTex


@article{BUT102035,
  author="Radim {Kolář} and Vratislav {Harabiš} and Jan {Odstrčilík}",
  title="Hybrid retinal image registration using phase correlation",
  annote="This paper deals with registration of retinal images, which were taken by highresolution digital colour fundus cameras. The proposed method describes successful application of phase correlation method. It combines several basic steps - global correction of shift, rotation and scaling, detection of landmarks, their correspondences and finally image registration using second-order polynomial model. The method is tested on two sets of images. The first set contains images from the diabetic patients where many retinal pathologies can disturb the registration process. The second set contains images from healthy subjects, which were acquired by different illumination conditions. The method was evaluated using four different criteria - tree objective and one subjective. These criteria are also compared. The achieved registration accuracy of the landmarks position error is 1.13 and 0.93 pixels for respective image sets. Finally, the simple scheme for retinal pathology visualisation of registered fundus pairs is presented.",
  address="Maney Publishing",
  chapter="102035",
  doi="10.1179/1743131X11Y.0000000065",
  howpublished="print",
  institution="Maney Publishing",
  number="4",
  volume="61",
  year="2013",
  month="may",
  pages="269--384",
  publisher="Maney Publishing",
  type="journal article - other"
}