Publication detail

IMPROVING QUALITY OF AUTOFLUORESCENCE IMAGES USING NON-RIGID IMAGE REGISTRATION

Kubecka L., Jan J., Kolar R., Jirik R.

Original Title

IMPROVING QUALITY OF AUTOFLUORESCENCE IMAGES USING NON-RIGID IMAGE REGISTRATION

Czech Title

Zlepšení kvality autofluorescenčních obrazů pomocí flexibilního lícování

English Title

IMPROVING QUALITY OF AUTOFLUORESCENCE IMAGES USING NON-RIGID IMAGE REGISTRATION

Type

conference paper

Language

en

Original Abstract

This work concerns quality improvement of autofluorescence retinal images by averaging of non-rigidly registered images. The necessity of using the elastic spatial transformation model is documented as well as the need for similarity criterion capable of dealing with the nonhomogenous and variable illumination of retinal images. The presented multilevel registration algorithm provides parameters of primarily affine and then B-spline free-form spatial transformation optimal with respect to the mutual information similarity criterion. The registration was tested on three modeled image sets of 100 images. The difference of artificially introduced pre-deformation displacement field and the displacement field found by our algorithm clearly showed the ability to compensate for the diverse modeled distortions. Further, the registration algorithm was used for improving quality of realistic retinal images using averaging of registered frames of image sequences.

Czech abstract

Práce popisuje metodu zlepšení autofluorescenčních retinálních obrazů pomocí potlačení šumu prostřednictvím průměrování flexibilně registrovaných obrazů. Lícování je vícestupńové a využívá nejprve affinní a následně B-splinové trasnformace. Metoda byla testována na simulovaných i skutečných retinálních obrazech a prokázala výrazné zlepšení kvality obrazu.

English abstract

This work concerns quality improvement of autofluorescence retinal images by averaging of non-rigidly registered images. The necessity of using the elastic spatial transformation model is documented as well as the need for similarity criterion capable of dealing with the nonhomogenous and variable illumination of retinal images. The presented multilevel registration algorithm provides parameters of primarily affine and then B-spline free-form spatial transformation optimal with respect to the mutual information similarity criterion. The registration was tested on three modeled image sets of 100 images. The difference of artificially introduced pre-deformation displacement field and the displacement field found by our algorithm clearly showed the ability to compensate for the diverse modeled distortions. Further, the registration algorithm was used for improving quality of realistic retinal images using averaging of registered frames of image sequences.

Keywords

image registration, image averaging, noise suppression, affine transform, flexible trasnforms, retinal images

RIV year

2006

Released

15.08.2006

Publisher

Univ. of Pisa

Location

Florence (Italy)

Pages from

357

Pages to

361

Pages count

5

URL

knihovna ÚBMI FEKT VUT

BibTex


@inproceedings{BUT24213,
  author="Libor {Kubečka} and Jiří {Jan} and Radim {Kolář} and Radovan {Jiřík}",
  title="IMPROVING QUALITY OF AUTOFLUORESCENCE IMAGES USING NON-RIGID IMAGE REGISTRATION",
  annote="This work concerns quality improvement of autofluorescence retinal images by averaging of non-rigidly registered images. The necessity of using the elastic spatial transformation model is documented as well as the need for similarity criterion capable of dealing with the nonhomogenous and variable illumination of retinal images. The presented multilevel registration algorithm provides parameters of primarily affine and then B-spline free-form spatial transformation optimal with respect to the mutual information similarity criterion. The registration was tested on three modeled image sets of 100 images. The difference of artificially introduced pre-deformation displacement field and the displacement field found by our algorithm clearly showed the ability to compensate for the diverse modeled distortions. Further, the registration algorithm was used for improving quality of realistic retinal images using averaging of registered frames of image sequences.",
  address="Univ. of Pisa",
  booktitle="Proc. 14th European Signal Processing Conf. EUSIPCO 2006",
  chapter="24213",
  edition="1",
  institution="Univ. of Pisa",
  year="2006",
  month="august",
  pages="357",
  publisher="Univ. of Pisa",
  type="conference paper"
}