Fast, Multi-Scale Image Processing on a Square Spiral Framework

Research output: Contribution to conferencePaper

Abstract

Efficient processing of digital images is a key consideration in many machine vision tasks. Traditional image processing approaches often struggle to meet this demand, particularly at the initial low-level of processing image pixels. To overcome this, we propose a spiral based processing approach which takes inspiration from the asymmetric lattice of interlocking cells found in the human visual system. Here we demonstrate the efficiency of the proposed spiral approach for multi-scale feature extraction. This is complemented by a biologically inspired image acquisition process which is used to capture nine image frames at different spatial locations. The results demonstrate that the biologically inspired spiral approach offers a faster alternative to corresponding traditional image processing approaches

Conference

ConferenceInternational Conference on Artificial Intelligence and Pattern Recognition
Abbreviated titleAIPR 2018
CountryChina
City Beijing
Period18/08/1820/08/18
Internet address

Fingerprint

Image processing
Image acquisition
Processing
Computer vision
Feature extraction
Pixels

Keywords

  • Fast Image Processing
  • Edge Detection
  • Multi-Scale Feature Extraction
  • Eye Tremor
  • Square Spiral Address Scheme

Cite this

Fegan, J., Kerr, D., Coleman, S., & Scotney, B. (2018). Fast, Multi-Scale Image Processing on a Square Spiral Framework. Paper presented at International Conference on Artificial Intelligence and Pattern Recognition , Beijing, China.
Fegan, John ; Kerr, Dermot ; Coleman, Sonya ; Scotney, Bryan. / Fast, Multi-Scale Image Processing on a Square Spiral Framework. Paper presented at International Conference on Artificial Intelligence and Pattern Recognition , Beijing, China.
@conference{b1a6e8d48a624788bd163fca242e7818,
title = "Fast, Multi-Scale Image Processing on a Square Spiral Framework",
abstract = "Efficient processing of digital images is a key consideration in many machine vision tasks. Traditional image processing approaches often struggle to meet this demand, particularly at the initial low-level of processing image pixels. To overcome this, we propose a spiral based processing approach which takes inspiration from the asymmetric lattice of interlocking cells found in the human visual system. Here we demonstrate the efficiency of the proposed spiral approach for multi-scale feature extraction. This is complemented by a biologically inspired image acquisition process which is used to capture nine image frames at different spatial locations. The results demonstrate that the biologically inspired spiral approach offers a faster alternative to corresponding traditional image processing approaches",
keywords = "Fast Image Processing, Edge Detection, Multi-Scale Feature Extraction, Eye Tremor, Square Spiral Address Scheme",
author = "John Fegan and Dermot Kerr and Sonya Coleman and Bryan Scotney",
year = "2018",
month = "8",
day = "18",
language = "English",
note = "International Conference on Artificial Intelligence and Pattern Recognition , AIPR 2018 ; Conference date: 18-08-2018 Through 20-08-2018",
url = "http://www.aipr.net",

}

Fegan, J, Kerr, D, Coleman, S & Scotney, B 2018, 'Fast, Multi-Scale Image Processing on a Square Spiral Framework' Paper presented at International Conference on Artificial Intelligence and Pattern Recognition , Beijing, China, 18/08/18 - 20/08/18, .

Fast, Multi-Scale Image Processing on a Square Spiral Framework. / Fegan, John; Kerr, Dermot; Coleman, Sonya; Scotney, Bryan.

2018. Paper presented at International Conference on Artificial Intelligence and Pattern Recognition , Beijing, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Fast, Multi-Scale Image Processing on a Square Spiral Framework

AU - Fegan, John

AU - Kerr, Dermot

AU - Coleman, Sonya

AU - Scotney, Bryan

PY - 2018/8/18

Y1 - 2018/8/18

N2 - Efficient processing of digital images is a key consideration in many machine vision tasks. Traditional image processing approaches often struggle to meet this demand, particularly at the initial low-level of processing image pixels. To overcome this, we propose a spiral based processing approach which takes inspiration from the asymmetric lattice of interlocking cells found in the human visual system. Here we demonstrate the efficiency of the proposed spiral approach for multi-scale feature extraction. This is complemented by a biologically inspired image acquisition process which is used to capture nine image frames at different spatial locations. The results demonstrate that the biologically inspired spiral approach offers a faster alternative to corresponding traditional image processing approaches

AB - Efficient processing of digital images is a key consideration in many machine vision tasks. Traditional image processing approaches often struggle to meet this demand, particularly at the initial low-level of processing image pixels. To overcome this, we propose a spiral based processing approach which takes inspiration from the asymmetric lattice of interlocking cells found in the human visual system. Here we demonstrate the efficiency of the proposed spiral approach for multi-scale feature extraction. This is complemented by a biologically inspired image acquisition process which is used to capture nine image frames at different spatial locations. The results demonstrate that the biologically inspired spiral approach offers a faster alternative to corresponding traditional image processing approaches

KW - Fast Image Processing

KW - Edge Detection

KW - Multi-Scale Feature Extraction

KW - Eye Tremor

KW - Square Spiral Address Scheme

M3 - Paper

ER -

Fegan J, Kerr D, Coleman S, Scotney B. Fast, Multi-Scale Image Processing on a Square Spiral Framework. 2018. Paper presented at International Conference on Artificial Intelligence and Pattern Recognition , Beijing, China.