Scaling images and image features via the renormalization group

Davi Geiger, Joao E. Kogler

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We set the problem to obtain high quality images and image features of different scales. We concentrate on a Markov image model described in a lattice by a Gaussian noise and a local regularization term depending upon the image discontinuities. An approximate self-similar property of the model is derived by a process of averaging over half of the lattice sites, known as the Renormalization Group approach. Two multiscale pyramid structures, one of images and the other of image discontinuities are then obtained. The course images generated by the proposed method are smooth and shows god contrast. The present approach, when applied in the reverse order, is capable of enlarging images while accounting for the original image features. We have demonstrated the quality of the derived pyramid by using it to help solve a segmentation problem.

Original languageEnglish (US)
Title of host publicationIEEE Computer Vision and Pattern Recognition
Editors Anon
PublisherPubl by IEEE
Pages47-53
Number of pages7
ISBN (Print)0818638826
StatePublished - 1993
EventProceedings of the 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - New York, NY, USA
Duration: Jun 15 1993Jun 18 1993

Other

OtherProceedings of the 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CityNew York, NY, USA
Period6/15/936/18/93

Fingerprint

Image quality

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Geiger, D., & Kogler, J. E. (1993). Scaling images and image features via the renormalization group. In Anon (Ed.), IEEE Computer Vision and Pattern Recognition (pp. 47-53). Publ by IEEE.

Scaling images and image features via the renormalization group. / Geiger, Davi; Kogler, Joao E.

IEEE Computer Vision and Pattern Recognition. ed. / Anon. Publ by IEEE, 1993. p. 47-53.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Geiger, D & Kogler, JE 1993, Scaling images and image features via the renormalization group. in Anon (ed.), IEEE Computer Vision and Pattern Recognition. Publ by IEEE, pp. 47-53, Proceedings of the 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA, 6/15/93.
Geiger D, Kogler JE. Scaling images and image features via the renormalization group. In Anon, editor, IEEE Computer Vision and Pattern Recognition. Publ by IEEE. 1993. p. 47-53
Geiger, Davi ; Kogler, Joao E. / Scaling images and image features via the renormalization group. IEEE Computer Vision and Pattern Recognition. editor / Anon. Publ by IEEE, 1993. pp. 47-53
@inproceedings{c904b52fe67c4fd8bcb1bbe1620033bd,
title = "Scaling images and image features via the renormalization group",
abstract = "We set the problem to obtain high quality images and image features of different scales. We concentrate on a Markov image model described in a lattice by a Gaussian noise and a local regularization term depending upon the image discontinuities. An approximate self-similar property of the model is derived by a process of averaging over half of the lattice sites, known as the Renormalization Group approach. Two multiscale pyramid structures, one of images and the other of image discontinuities are then obtained. The course images generated by the proposed method are smooth and shows god contrast. The present approach, when applied in the reverse order, is capable of enlarging images while accounting for the original image features. We have demonstrated the quality of the derived pyramid by using it to help solve a segmentation problem.",
author = "Davi Geiger and Kogler, {Joao E.}",
year = "1993",
language = "English (US)",
isbn = "0818638826",
pages = "47--53",
editor = "Anon",
booktitle = "IEEE Computer Vision and Pattern Recognition",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Scaling images and image features via the renormalization group

AU - Geiger, Davi

AU - Kogler, Joao E.

PY - 1993

Y1 - 1993

N2 - We set the problem to obtain high quality images and image features of different scales. We concentrate on a Markov image model described in a lattice by a Gaussian noise and a local regularization term depending upon the image discontinuities. An approximate self-similar property of the model is derived by a process of averaging over half of the lattice sites, known as the Renormalization Group approach. Two multiscale pyramid structures, one of images and the other of image discontinuities are then obtained. The course images generated by the proposed method are smooth and shows god contrast. The present approach, when applied in the reverse order, is capable of enlarging images while accounting for the original image features. We have demonstrated the quality of the derived pyramid by using it to help solve a segmentation problem.

AB - We set the problem to obtain high quality images and image features of different scales. We concentrate on a Markov image model described in a lattice by a Gaussian noise and a local regularization term depending upon the image discontinuities. An approximate self-similar property of the model is derived by a process of averaging over half of the lattice sites, known as the Renormalization Group approach. Two multiscale pyramid structures, one of images and the other of image discontinuities are then obtained. The course images generated by the proposed method are smooth and shows god contrast. The present approach, when applied in the reverse order, is capable of enlarging images while accounting for the original image features. We have demonstrated the quality of the derived pyramid by using it to help solve a segmentation problem.

UR - http://www.scopus.com/inward/record.url?scp=0027835849&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027835849&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027835849

SN - 0818638826

SP - 47

EP - 53

BT - IEEE Computer Vision and Pattern Recognition

A2 - Anon, null

PB - Publ by IEEE

ER -