Detail publikace

Automatic adaptive optics retinal images montaging

VALTEROVÁ, E.

Originální název

Automatic adaptive optics retinal images montaging

Anglický název

Automatic adaptive optics retinal images montaging

Jazyk

en

Originální abstrakt

The adaptive optics images capture limited field of view. Nevertheless, the quantitative retina assessment requires analysis over extended areas captured by images on various retina positions. The fully automated method for image registration and montaging is presented. The method utilizes scale invariant feature transform (SIFT) for feature extraction from preprocessed images. The method is tested on 200 images of normal healthy patients. The montages of 20 eyes were created and evaluated by normalized mutual information metrics and the results showed high alignment accuracy.

Anglický abstrakt

The adaptive optics images capture limited field of view. Nevertheless, the quantitative retina assessment requires analysis over extended areas captured by images on various retina positions. The fully automated method for image registration and montaging is presented. The method utilizes scale invariant feature transform (SIFT) for feature extraction from preprocessed images. The method is tested on 200 images of normal healthy patients. The montages of 20 eyes were created and evaluated by normalized mutual information metrics and the results showed high alignment accuracy.

Dokumenty

BibTex 


@inproceedings{BUT172265,
  author="Eva {Orságová}",
  title="Automatic adaptive optics retinal images montaging",
  annote="The adaptive optics images capture limited field of view. Nevertheless, the quantitative retina assessment requires analysis over extended areas captured by images on various retina positions. The fully automated method for image registration and montaging is presented. The method utilizes scale invariant feature transform (SIFT) for feature extraction from preprocessed images. The method is tested on 200 images of normal healthy patients. The montages of 20 eyes were created and evaluated by normalized mutual information metrics and the results showed high alignment accuracy.",
  address="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  booktitle="Proceedings of the 27th Conference STUDENT EEICT 2021 selected papers",
  chapter="172265",
  doi="10.13164/eeict.2021.121",
  edition="1",
  howpublished="online",
  institution="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  year="2021",
  month="april",
  pages="121--125",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  type="conference paper"
}