The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim
—This paper presents an analysis of three feature extraction techniques which are the shape-based, Zernike moments and Discrete Wavelet Transform for fastener recognition. RGB colour features are also added to these major feature extractors to enhance the classification result. The classifier u...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
UiTM Press
2016
|
Subjects: | |
Online Access: | https://ir.uitm.edu.my/id/eprint/63005/1/63005.pdf https://ir.uitm.edu.my/id/eprint/63005/ https://jeesr.uitm.edu.my/v1/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uitm.ir.63005 |
---|---|
record_format |
eprints |
spelling |
my.uitm.ir.630052022-06-28T10:38:45Z https://ir.uitm.edu.my/id/eprint/63005/ The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim Mustafa Kamal, N. D. Jalil, N. Hashim, H. Pattern recognition systems —This paper presents an analysis of three feature extraction techniques which are the shape-based, Zernike moments and Discrete Wavelet Transform for fastener recognition. RGB colour features are also added to these major feature extractors to enhance the classification result. The classifier used in this experiment is back propagation neural network and the result in general is strengthen using ten-fold cross validation. The result is measured using percentage accuracy and Kappa statistics. The overall results showed that the best feature extraction techniques are Zernike moment group 3 and DWT both with added colour features. UiTM Press 2016-12 Article PeerReviewed text en https://ir.uitm.edu.my/id/eprint/63005/1/63005.pdf The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim. (2016) Journal of Electrical and Electronic Systems Research (JEESR), 9: 8. pp. 43-51. ISSN 1985-5389 https://jeesr.uitm.edu.my/v1/ |
institution |
Universiti Teknologi Mara |
building |
Tun Abdul Razak Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Mara |
content_source |
UiTM Institutional Repository |
url_provider |
http://ir.uitm.edu.my/ |
language |
English |
topic |
Pattern recognition systems |
spellingShingle |
Pattern recognition systems Mustafa Kamal, N. D. Jalil, N. Hashim, H. The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim |
description |
—This paper presents an analysis of three feature
extraction techniques which are the shape-based, Zernike
moments and Discrete Wavelet Transform for fastener
recognition. RGB colour features are also added to these major
feature extractors to enhance the classification result. The
classifier used in this experiment is back propagation neural
network and the result in general is strengthen using ten-fold
cross validation. The result is measured using percentage
accuracy and Kappa statistics. The overall results showed that
the best feature extraction techniques are Zernike moment
group 3 and DWT both with added colour features. |
format |
Article |
author |
Mustafa Kamal, N. D. Jalil, N. Hashim, H. |
author_facet |
Mustafa Kamal, N. D. Jalil, N. Hashim, H. |
author_sort |
Mustafa Kamal, N. D. |
title |
The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim |
title_short |
The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim |
title_full |
The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim |
title_fullStr |
The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim |
title_full_unstemmed |
The analysis of shape-based, DWT and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / N. D. Mustaffa Kamal, N. Jalil and H. Hashim |
title_sort |
analysis of shape-based, dwt and zernike moments feature extraction techniques for fasterner recognition using 10-fold cross validation multilayer perceptrons / n. d. mustaffa kamal, n. jalil and h. hashim |
publisher |
UiTM Press |
publishDate |
2016 |
url |
https://ir.uitm.edu.my/id/eprint/63005/1/63005.pdf https://ir.uitm.edu.my/id/eprint/63005/ https://jeesr.uitm.edu.my/v1/ |
_version_ |
1738513997484785664 |
score |
13.18916 |