Gradient Magnitude Based Normalised Convolution

Ahmad Al-Kabbany, SA Coleman, D Kerr

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

Abstract

Although image data can often be sparse for a variety of different reasons, standard image processing techniques require the use of complete image data. Therefore sparse image data must undergo reconstruction to yield complete images prior to any subsequent processing. Highly accurate image reconstruction techniques tend to be expensive to implement whilst simpler techniques, such as image interpolation, are usually not adequate to support subsequent reliable image processing. A common approach to image reconstruction is normalised convolution; we present a modified approach to normalised convolution which is based on the sparse image content and we demonstrate that accurate reconstruction is achieved yielding better image processing results than the current standard normalised convolution.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages76-82
Number of pages7
Publication statusPublished - 2 Oct 2015
EventIrish Machine Vision and Image Processing Conference 2015 - Trinity College, Dublin, Ireland .
Duration: 2 Oct 2015 → …

Conference

ConferenceIrish Machine Vision and Image Processing Conference 2015
Period2/10/15 → …

Fingerprint

Convolution
Image processing
Image reconstruction
Interpolation
Processing

Keywords

  • Image reconstruction
  • Normalised convolution

Cite this

Al-Kabbany, A., Coleman, SA., & Kerr, D. (2015). Gradient Magnitude Based Normalised Convolution. In Unknown Host Publication (pp. 76-82)
Al-Kabbany, Ahmad ; Coleman, SA ; Kerr, D. / Gradient Magnitude Based Normalised Convolution. Unknown Host Publication. 2015. pp. 76-82
@inproceedings{f1a7b79d57224d84a9e5f847a7392ce5,
title = "Gradient Magnitude Based Normalised Convolution",
abstract = "Although image data can often be sparse for a variety of different reasons, standard image processing techniques require the use of complete image data. Therefore sparse image data must undergo reconstruction to yield complete images prior to any subsequent processing. Highly accurate image reconstruction techniques tend to be expensive to implement whilst simpler techniques, such as image interpolation, are usually not adequate to support subsequent reliable image processing. A common approach to image reconstruction is normalised convolution; we present a modified approach to normalised convolution which is based on the sparse image content and we demonstrate that accurate reconstruction is achieved yielding better image processing results than the current standard normalised convolution.",
keywords = "Image reconstruction, Normalised convolution",
author = "Ahmad Al-Kabbany and SA Coleman and D Kerr",
year = "2015",
month = "10",
day = "2",
language = "English",
isbn = "978-0-9934207-0-2",
pages = "76--82",
booktitle = "Unknown Host Publication",

}

Al-Kabbany, A, Coleman, SA & Kerr, D 2015, Gradient Magnitude Based Normalised Convolution. in Unknown Host Publication. pp. 76-82, Irish Machine Vision and Image Processing Conference 2015, 2/10/15.

Gradient Magnitude Based Normalised Convolution. / Al-Kabbany, Ahmad; Coleman, SA; Kerr, D.

Unknown Host Publication. 2015. p. 76-82.

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

TY - GEN

T1 - Gradient Magnitude Based Normalised Convolution

AU - Al-Kabbany, Ahmad

AU - Coleman, SA

AU - Kerr, D

PY - 2015/10/2

Y1 - 2015/10/2

N2 - Although image data can often be sparse for a variety of different reasons, standard image processing techniques require the use of complete image data. Therefore sparse image data must undergo reconstruction to yield complete images prior to any subsequent processing. Highly accurate image reconstruction techniques tend to be expensive to implement whilst simpler techniques, such as image interpolation, are usually not adequate to support subsequent reliable image processing. A common approach to image reconstruction is normalised convolution; we present a modified approach to normalised convolution which is based on the sparse image content and we demonstrate that accurate reconstruction is achieved yielding better image processing results than the current standard normalised convolution.

AB - Although image data can often be sparse for a variety of different reasons, standard image processing techniques require the use of complete image data. Therefore sparse image data must undergo reconstruction to yield complete images prior to any subsequent processing. Highly accurate image reconstruction techniques tend to be expensive to implement whilst simpler techniques, such as image interpolation, are usually not adequate to support subsequent reliable image processing. A common approach to image reconstruction is normalised convolution; we present a modified approach to normalised convolution which is based on the sparse image content and we demonstrate that accurate reconstruction is achieved yielding better image processing results than the current standard normalised convolution.

KW - Image reconstruction

KW - Normalised convolution

M3 - Conference contribution

SN - 978-0-9934207-0-2

SP - 76

EP - 82

BT - Unknown Host Publication

ER -

Al-Kabbany A, Coleman SA, Kerr D. Gradient Magnitude Based Normalised Convolution. In Unknown Host Publication. 2015. p. 76-82