Rotation-invariant pattern signature

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

Abstract

We propose a 'signature' for rotation-invariant representation of local image structure. The signature is a complex-valued vector constructed analytically from the projections of the image onto a set of oriented basis kernels. The components of the signature form an over-complete set of algebraic invariants, but are chosen to avoid instabilities associated with previously developed algebraic invariants. We demonstrate the use of this signature for representing and classifying junctions in grayscale imagery.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Image Processing
Editors Anon
PublisherIEEE
Pages185-188
Number of pages4
Volume3
StatePublished - 1996
EventProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) - Lausanne, Switz
Duration: Sep 16 1996Sep 19 1996

Other

OtherProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)
CityLausanne, Switz
Period9/16/969/19/96

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Simoncelli, E. (1996). Rotation-invariant pattern signature. In Anon (Ed.), IEEE International Conference on Image Processing (Vol. 3, pp. 185-188). IEEE.

Rotation-invariant pattern signature. / Simoncelli, Eero.

IEEE International Conference on Image Processing. ed. / Anon. Vol. 3 IEEE, 1996. p. 185-188.

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

Simoncelli, E 1996, Rotation-invariant pattern signature. in Anon (ed.), IEEE International Conference on Image Processing. vol. 3, IEEE, pp. 185-188, Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3), Lausanne, Switz, 9/16/96.
Simoncelli E. Rotation-invariant pattern signature. In Anon, editor, IEEE International Conference on Image Processing. Vol. 3. IEEE. 1996. p. 185-188
Simoncelli, Eero. / Rotation-invariant pattern signature. IEEE International Conference on Image Processing. editor / Anon. Vol. 3 IEEE, 1996. pp. 185-188
@inproceedings{f24f6e9359b448208362d9eddbdec964,
title = "Rotation-invariant pattern signature",
abstract = "We propose a 'signature' for rotation-invariant representation of local image structure. The signature is a complex-valued vector constructed analytically from the projections of the image onto a set of oriented basis kernels. The components of the signature form an over-complete set of algebraic invariants, but are chosen to avoid instabilities associated with previously developed algebraic invariants. We demonstrate the use of this signature for representing and classifying junctions in grayscale imagery.",
author = "Eero Simoncelli",
year = "1996",
language = "English (US)",
volume = "3",
pages = "185--188",
editor = "Anon",
booktitle = "IEEE International Conference on Image Processing",
publisher = "IEEE",

}

TY - GEN

T1 - Rotation-invariant pattern signature

AU - Simoncelli, Eero

PY - 1996

Y1 - 1996

N2 - We propose a 'signature' for rotation-invariant representation of local image structure. The signature is a complex-valued vector constructed analytically from the projections of the image onto a set of oriented basis kernels. The components of the signature form an over-complete set of algebraic invariants, but are chosen to avoid instabilities associated with previously developed algebraic invariants. We demonstrate the use of this signature for representing and classifying junctions in grayscale imagery.

AB - We propose a 'signature' for rotation-invariant representation of local image structure. The signature is a complex-valued vector constructed analytically from the projections of the image onto a set of oriented basis kernels. The components of the signature form an over-complete set of algebraic invariants, but are chosen to avoid instabilities associated with previously developed algebraic invariants. We demonstrate the use of this signature for representing and classifying junctions in grayscale imagery.

UR - http://www.scopus.com/inward/record.url?scp=0030402595&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030402595&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 185

EP - 188

BT - IEEE International Conference on Image Processing

A2 - Anon, null

PB - IEEE

ER -