Biologically Motivated Feature Extraction

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

1 Citation (Scopus)

Abstract

We present a biologically motivated approach to fast feature extraction on hexagonal pixel based images using the concept of eye tremor in combination with the use of the spiral architecture and convolution of non-overlapping Laplacian masks. We generate seven feature maps “a-trous” that can be combined into a single complete feature map, and we demonstrate that this approach is significantly faster than the use of conventional spiral convolution or the use of a neighbourhood address look-up table on hexagonal images
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages605-615
Number of pages10
Volume6978/2
DOIs
Publication statusPublished - 14 Sep 2011
Event16th International Conference on Image Analysis and Processing - Ravenna, Italy
Duration: 14 Sep 2011 → …

Conference

Conference16th International Conference on Image Analysis and Processing
Period14/09/11 → …

Fingerprint

Convolution
Feature extraction
Masks
Pixels

Cite this

Coleman, SA ; Scotney, BW ; Gardiner, B. / Biologically Motivated Feature Extraction. Unknown Host Publication. Vol. 6978/2 2011. pp. 605-615
@inproceedings{da80f4ee274240a6af9ec342b454c300,
title = "Biologically Motivated Feature Extraction",
abstract = "We present a biologically motivated approach to fast feature extraction on hexagonal pixel based images using the concept of eye tremor in combination with the use of the spiral architecture and convolution of non-overlapping Laplacian masks. We generate seven feature maps “a-trous” that can be combined into a single complete feature map, and we demonstrate that this approach is significantly faster than the use of conventional spiral convolution or the use of a neighbourhood address look-up table on hexagonal images",
author = "SA Coleman and BW Scotney and B Gardiner",
year = "2011",
month = "9",
day = "14",
doi = "10.1007/978-3-642-24085-0_62",
language = "English",
isbn = "978-3-642-24084-3",
volume = "6978/2",
pages = "605--615",
booktitle = "Unknown Host Publication",

}

Coleman, SA, Scotney, BW & Gardiner, B 2011, Biologically Motivated Feature Extraction. in Unknown Host Publication. vol. 6978/2, pp. 605-615, 16th International Conference on Image Analysis and Processing, 14/09/11. https://doi.org/10.1007/978-3-642-24085-0_62

Biologically Motivated Feature Extraction. / Coleman, SA; Scotney, BW; Gardiner, B.

Unknown Host Publication. Vol. 6978/2 2011. p. 605-615.

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

TY - GEN

T1 - Biologically Motivated Feature Extraction

AU - Coleman, SA

AU - Scotney, BW

AU - Gardiner, B

PY - 2011/9/14

Y1 - 2011/9/14

N2 - We present a biologically motivated approach to fast feature extraction on hexagonal pixel based images using the concept of eye tremor in combination with the use of the spiral architecture and convolution of non-overlapping Laplacian masks. We generate seven feature maps “a-trous” that can be combined into a single complete feature map, and we demonstrate that this approach is significantly faster than the use of conventional spiral convolution or the use of a neighbourhood address look-up table on hexagonal images

AB - We present a biologically motivated approach to fast feature extraction on hexagonal pixel based images using the concept of eye tremor in combination with the use of the spiral architecture and convolution of non-overlapping Laplacian masks. We generate seven feature maps “a-trous” that can be combined into a single complete feature map, and we demonstrate that this approach is significantly faster than the use of conventional spiral convolution or the use of a neighbourhood address look-up table on hexagonal images

U2 - 10.1007/978-3-642-24085-0_62

DO - 10.1007/978-3-642-24085-0_62

M3 - Conference contribution

SN - 978-3-642-24084-3

VL - 6978/2

SP - 605

EP - 615

BT - Unknown Host Publication

ER -