Biologically Motivated Feature Extraction Using the Spiral Architecture

BW Scotney; SA Coleman; B Gardiner

doi:10.1109/ICIP.2011.6116077

Biologically Motivated Feature Extraction Using the Spiral Architecture

BW Scotney, SA Coleman, B Gardiner

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Citations (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 gradient 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.

Original language	English
Title of host publication	Unknown Host Publication
Publisher	IEEE Computer Society
Pages	221-224
Number of pages	4
ISBN (Print)	978-1-4577-1304-0
DOIs	https://doi.org/10.1109/ICIP.2011.6116077
Publication status	Published (in print/issue) - 11 Sept 2011
Event	18th IEEE International Conference on Image Processing (ICIP), - Brussels, Belgium Duration: 11 Sept 2011 → …

Conference

Conference	18th IEEE International Conference on Image Processing (ICIP),
Period	11/09/11 → …

Access to Document

10.1109/ICIP.2011.6116077

Cite this

@inproceedings{4bc92f9181fd40be9449d54a9fdb6419,

title = "Biologically Motivated Feature Extraction Using the Spiral Architecture",

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 gradient 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 = "BW Scotney and SA Coleman and B Gardiner",

year = "2011",

month = sep,

day = "11",

doi = "10.1109/ICIP.2011.6116077",

language = "English",

isbn = "978-1-4577-1304-0",

pages = "221--224",

booktitle = "Unknown Host Publication",

publisher = "IEEE Computer Society",

address = "United States",

note = "18th IEEE International Conference on Image Processing (ICIP), ; Conference date: 11-09-2011",

}

TY - GEN

T1 - Biologically Motivated Feature Extraction Using the Spiral Architecture

AU - Scotney, BW

AU - Coleman, SA

AU - Gardiner, B

PY - 2011/9/11

Y1 - 2011/9/11

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 gradient 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 gradient 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 - 10.1109/ICIP.2011.6116077

DO - 10.1109/ICIP.2011.6116077

M3 - Conference contribution

SN - 978-1-4577-1304-0

SP - 221

EP - 224

BT - Unknown Host Publication

PB - IEEE Computer Society

T2 - 18th IEEE International Conference on Image Processing (ICIP),

Y2 - 11 September 2011

ER -

Biologically Motivated Feature Extraction Using the Spiral Architecture

Abstract

Conference

Access to Document

Fingerprint

Cite this