Coarse Scale Feature Extraction Using the Spiral Architecture Structure

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

1 Citation (Scopus)

Abstract

The Spiral Architecture has been developed as a fast way ofindexing a hexagonal pixel-based image. In combinationwith spiral addition and spiral multiplication, methods havebeen developed for hexagonal image processing operationssuch as translation and rotation. Using the SpiralArchitecture as the basis for our operator structure, wepresent a general approach to the computation of adaptivecoarse scale Laplacian operators for use on hexagonal pixelbasedimages. We evaluate the proposed operators usingsimulated hexagonal images and demonstrate improvedperformance when compared with rectangular Laplacianoperators such as Marr-Hildreth.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages2370-2373
Number of pages4
DOIs
Publication statusPublished - 23 Aug 2010
EventIntenational Conference on Pattern Recognition - Turkey
Duration: 23 Aug 2010 → …

Conference

ConferenceIntenational Conference on Pattern Recognition
Period23/08/10 → …

Fingerprint

Mathematical operators
Feature extraction
Image processing
Pixels

Cite this

@inproceedings{11fef1b215e142d09b9b4be21a38f8bf,
title = "Coarse Scale Feature Extraction Using the Spiral Architecture Structure",
abstract = "The Spiral Architecture has been developed as a fast way ofindexing a hexagonal pixel-based image. In combinationwith spiral addition and spiral multiplication, methods havebeen developed for hexagonal image processing operationssuch as translation and rotation. Using the SpiralArchitecture as the basis for our operator structure, wepresent a general approach to the computation of adaptivecoarse scale Laplacian operators for use on hexagonal pixelbasedimages. We evaluate the proposed operators usingsimulated hexagonal images and demonstrate improvedperformance when compared with rectangular Laplacianoperators such as Marr-Hildreth.",
author = "SA Coleman and B Gardiner and BW Scotney",
year = "2010",
month = "8",
day = "23",
doi = "10.1109/ICPR.2010.580",
language = "English",
isbn = "1051-4651/10",
pages = "2370--2373",
booktitle = "Unknown Host Publication",

}

Coleman, SA, Gardiner, B & Scotney, BW 2010, Coarse Scale Feature Extraction Using the Spiral Architecture Structure. in Unknown Host Publication. pp. 2370-2373, Intenational Conference on Pattern Recognition, 23/08/10. https://doi.org/10.1109/ICPR.2010.580

Coarse Scale Feature Extraction Using the Spiral Architecture Structure. / Coleman, SA; Gardiner, B; Scotney, BW.

Unknown Host Publication. 2010. p. 2370-2373.

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

TY - GEN

T1 - Coarse Scale Feature Extraction Using the Spiral Architecture Structure

AU - Coleman, SA

AU - Gardiner, B

AU - Scotney, BW

PY - 2010/8/23

Y1 - 2010/8/23

N2 - The Spiral Architecture has been developed as a fast way ofindexing a hexagonal pixel-based image. In combinationwith spiral addition and spiral multiplication, methods havebeen developed for hexagonal image processing operationssuch as translation and rotation. Using the SpiralArchitecture as the basis for our operator structure, wepresent a general approach to the computation of adaptivecoarse scale Laplacian operators for use on hexagonal pixelbasedimages. We evaluate the proposed operators usingsimulated hexagonal images and demonstrate improvedperformance when compared with rectangular Laplacianoperators such as Marr-Hildreth.

AB - The Spiral Architecture has been developed as a fast way ofindexing a hexagonal pixel-based image. In combinationwith spiral addition and spiral multiplication, methods havebeen developed for hexagonal image processing operationssuch as translation and rotation. Using the SpiralArchitecture as the basis for our operator structure, wepresent a general approach to the computation of adaptivecoarse scale Laplacian operators for use on hexagonal pixelbasedimages. We evaluate the proposed operators usingsimulated hexagonal images and demonstrate improvedperformance when compared with rectangular Laplacianoperators such as Marr-Hildreth.

U2 - 10.1109/ICPR.2010.580

DO - 10.1109/ICPR.2010.580

M3 - Conference contribution

SN - 1051-4651/10

SP - 2370

EP - 2373

BT - Unknown Host Publication

ER -