Steerable wedge filters

Eero Simoncelli, H. Farid

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

Abstract

Steerable filters, as developed by Freeman and Adelson, are a class of rotation-invariant linear operators that may be used to analyze local orientation patterns in imagery. The most common examples of such operators are directional derivatives of Gaussians and their 2-D Hilbert transforms. The inherent symmetry of these filters produces an orientation response that is periodic with period π, even when the underlying image structure does not have such symmetry. This problem may be alleviated by reconsidering the full class of steerable filters. In this paper, we develop a family of even- and odd- symmetric steerable filters that have a spatially asymmetric 'wedge-like' shape and are optimally localized in their orientation response. Unlike the original steerable filters, these filters are not based on directional derivatives and the Hilbert transform relationship is imposed on their angular components. We demonstrate the ability of these filters to properly represent oriented structures.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Computer Vision
Editors Anon
PublisherIEEE
Pages189-194
Number of pages6
StatePublished - 1995
EventProceedings of the 5th International Conference on Computer Vision - Cambridge, MA, USA
Duration: Jun 20 1995Jun 23 1995

Other

OtherProceedings of the 5th International Conference on Computer Vision
CityCambridge, MA, USA
Period6/20/956/23/95

Fingerprint

Derivatives

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Simoncelli, E., & Farid, H. (1995). Steerable wedge filters. In Anon (Ed.), IEEE International Conference on Computer Vision (pp. 189-194). IEEE.

Steerable wedge filters. / Simoncelli, Eero; Farid, H.

IEEE International Conference on Computer Vision. ed. / Anon. IEEE, 1995. p. 189-194.

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

Simoncelli, E & Farid, H 1995, Steerable wedge filters. in Anon (ed.), IEEE International Conference on Computer Vision. IEEE, pp. 189-194, Proceedings of the 5th International Conference on Computer Vision, Cambridge, MA, USA, 6/20/95.
Simoncelli E, Farid H. Steerable wedge filters. In Anon, editor, IEEE International Conference on Computer Vision. IEEE. 1995. p. 189-194
Simoncelli, Eero ; Farid, H. / Steerable wedge filters. IEEE International Conference on Computer Vision. editor / Anon. IEEE, 1995. pp. 189-194
@inproceedings{a34e509c5e4b411cb87ebcdbb324e150,
title = "Steerable wedge filters",
abstract = "Steerable filters, as developed by Freeman and Adelson, are a class of rotation-invariant linear operators that may be used to analyze local orientation patterns in imagery. The most common examples of such operators are directional derivatives of Gaussians and their 2-D Hilbert transforms. The inherent symmetry of these filters produces an orientation response that is periodic with period π, even when the underlying image structure does not have such symmetry. This problem may be alleviated by reconsidering the full class of steerable filters. In this paper, we develop a family of even- and odd- symmetric steerable filters that have a spatially asymmetric 'wedge-like' shape and are optimally localized in their orientation response. Unlike the original steerable filters, these filters are not based on directional derivatives and the Hilbert transform relationship is imposed on their angular components. We demonstrate the ability of these filters to properly represent oriented structures.",
author = "Eero Simoncelli and H. Farid",
year = "1995",
language = "English (US)",
pages = "189--194",
editor = "Anon",
booktitle = "IEEE International Conference on Computer Vision",
publisher = "IEEE",

}

TY - GEN

T1 - Steerable wedge filters

AU - Simoncelli, Eero

AU - Farid, H.

PY - 1995

Y1 - 1995

N2 - Steerable filters, as developed by Freeman and Adelson, are a class of rotation-invariant linear operators that may be used to analyze local orientation patterns in imagery. The most common examples of such operators are directional derivatives of Gaussians and their 2-D Hilbert transforms. The inherent symmetry of these filters produces an orientation response that is periodic with period π, even when the underlying image structure does not have such symmetry. This problem may be alleviated by reconsidering the full class of steerable filters. In this paper, we develop a family of even- and odd- symmetric steerable filters that have a spatially asymmetric 'wedge-like' shape and are optimally localized in their orientation response. Unlike the original steerable filters, these filters are not based on directional derivatives and the Hilbert transform relationship is imposed on their angular components. We demonstrate the ability of these filters to properly represent oriented structures.

AB - Steerable filters, as developed by Freeman and Adelson, are a class of rotation-invariant linear operators that may be used to analyze local orientation patterns in imagery. The most common examples of such operators are directional derivatives of Gaussians and their 2-D Hilbert transforms. The inherent symmetry of these filters produces an orientation response that is periodic with period π, even when the underlying image structure does not have such symmetry. This problem may be alleviated by reconsidering the full class of steerable filters. In this paper, we develop a family of even- and odd- symmetric steerable filters that have a spatially asymmetric 'wedge-like' shape and are optimally localized in their orientation response. Unlike the original steerable filters, these filters are not based on directional derivatives and the Hilbert transform relationship is imposed on their angular components. We demonstrate the ability of these filters to properly represent oriented structures.

UR - http://www.scopus.com/inward/record.url?scp=0029234210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029234210&partnerID=8YFLogxK

M3 - Conference contribution

SP - 189

EP - 194

BT - IEEE International Conference on Computer Vision

A2 - Anon, null

PB - IEEE

ER -