A study of neural-network-based classifiers for material classification

In this paper, the performance of the commonly used neural-network-based classifiers is investigated on solving a classification problem which aims to identify the object nature based on surface features of the object. When the surface data is obtained, a proposed feature extraction method is used t...

Full description

Bibliographic Details
Main Authors: Lam, H., Ekong, U., Liu, H., Xiao, B., Araujo, H., Ling, S.H., Chan, Kit Yan
Format: Journal Article
Published: Elsevier BV 2014
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/5196
_version_ 1848744728470749184
author Lam, H.
Ekong, U.
Liu, H.
Xiao, B.
Araujo, H.
Ling, S.H.
Chan, Kit Yan
author_facet Lam, H.
Ekong, U.
Liu, H.
Xiao, B.
Araujo, H.
Ling, S.H.
Chan, Kit Yan
author_sort Lam, H.
building Curtin Institutional Repository
collection Online Access
description In this paper, the performance of the commonly used neural-network-based classifiers is investigated on solving a classification problem which aims to identify the object nature based on surface features of the object. When the surface data is obtained, a proposed feature extraction method is used to extract the surface feature of the object. The extracted features are then used as the inputs for the classifier. This research studies eighteen household objects which are requisite to our daily life. Six commonly used neural-network-based classifiers, namely one-against-all, weighted one-against-all, binary coded, parallel-structured, weighted parallel structured and tree-structured, are investigated. The performance for the six neural-network-based classifiers is evaluated based on recognition accuracy for individual object. Also, two traditional classifiers, namely k-nearest neighbor classifier and naïve Bayes classifier, are employed for comparison purposes. To evaluate robustness property of the classifiers, the original data is contaminated with Gaussian white noise. Experimental results show that the parallel-structured, tree-structured and the naïve Bayes classifiers outperform the others under the original data. The tree- structured classifier demonstrates the best robustness property under the noisy data.
first_indexed 2025-11-14T06:06:05Z
format Journal Article
id curtin-20.500.11937-5196
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:06:05Z
publishDate 2014
publisher Elsevier BV
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-51962017-09-13T14:45:10Z A study of neural-network-based classifiers for material classification Lam, H. Ekong, U. Liu, H. Xiao, B. Araujo, H. Ling, S.H. Chan, Kit Yan Neural Networks Material Classification Classifier In this paper, the performance of the commonly used neural-network-based classifiers is investigated on solving a classification problem which aims to identify the object nature based on surface features of the object. When the surface data is obtained, a proposed feature extraction method is used to extract the surface feature of the object. The extracted features are then used as the inputs for the classifier. This research studies eighteen household objects which are requisite to our daily life. Six commonly used neural-network-based classifiers, namely one-against-all, weighted one-against-all, binary coded, parallel-structured, weighted parallel structured and tree-structured, are investigated. The performance for the six neural-network-based classifiers is evaluated based on recognition accuracy for individual object. Also, two traditional classifiers, namely k-nearest neighbor classifier and naïve Bayes classifier, are employed for comparison purposes. To evaluate robustness property of the classifiers, the original data is contaminated with Gaussian white noise. Experimental results show that the parallel-structured, tree-structured and the naïve Bayes classifiers outperform the others under the original data. The tree- structured classifier demonstrates the best robustness property under the noisy data. 2014 Journal Article http://hdl.handle.net/20.500.11937/5196 10.1016/j.neucom.2014.05.019 Elsevier BV restricted
spellingShingle Neural Networks
Material Classification
Classifier
Lam, H.
Ekong, U.
Liu, H.
Xiao, B.
Araujo, H.
Ling, S.H.
Chan, Kit Yan
A study of neural-network-based classifiers for material classification
title A study of neural-network-based classifiers for material classification
title_full A study of neural-network-based classifiers for material classification
title_fullStr A study of neural-network-based classifiers for material classification
title_full_unstemmed A study of neural-network-based classifiers for material classification
title_short A study of neural-network-based classifiers for material classification
title_sort study of neural-network-based classifiers for material classification
topic Neural Networks
Material Classification
Classifier
url http://hdl.handle.net/20.500.11937/5196