Cover Image

Transfer learning approach in automatic tropical wood recognition system

Automatic recognition of tropical wood species is a very challenging task due to the lack of discriminative features among intra wood species and very discriminative features among inter class species. While many conventional pattern recognition algorithms have been implemented and proven to solve w...

Full description

Saved in:
Bibliographic Details
Main Authors: Yusof, Rubiyah, Ahmad, Azlin, Mohd. Khairuddin, Anis Salwa, Khairuddin, Uswah, Nik Azmi, Nik Mohamad Aizuddin, Rosli, Nenny Ruthfalydia
Format: Book Section
Published: Springer 2020
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/id/eprint/92239/
http://dx.doi.org/10.1088/1757-899X/849/1/012039
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.92239
record_format eprints
spelling my.utm.922392021-09-28T07:34:34Z http://eprints.utm.my/id/eprint/92239/ Transfer learning approach in automatic tropical wood recognition system Yusof, Rubiyah Ahmad, Azlin Mohd. Khairuddin, Anis Salwa Khairuddin, Uswah Nik Azmi, Nik Mohamad Aizuddin Rosli, Nenny Ruthfalydia T Technology (General) Automatic recognition of tropical wood species is a very challenging task due to the lack of discriminative features among intra wood species and very discriminative features among inter class species. While many conventional pattern recognition algorithms have been implemented and proven to solve wood image classification with 100% accuracy, when using deep learning however, the classification accuracy drops tremendously to only 36.3% due to small number of training samples. Deep learning requires large number of samples in order to work well, unfortunately, wood samples provided by the national forest institute are limited. In this paper, we explore the use of transfer learning in deep neural network for the classification of tropical wood species based on image analysis. Several model of deep learning techniques are tested and results have shown that the classification performance after transfer learning was added reaches 100% accuracy. Springer 2020 Book Section PeerReviewed Yusof, Rubiyah and Ahmad, Azlin and Mohd. Khairuddin, Anis Salwa and Khairuddin, Uswah and Nik Azmi, Nik Mohamad Aizuddin and Rosli, Nenny Ruthfalydia (2020) Transfer learning approach in automatic tropical wood recognition system. In: Mechanisms and Machine Science. Springer, pp. 1225-1233. ISBN 978-3-030-27052-0 http://dx.doi.org/10.1088/1757-899X/849/1/012039
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic T Technology (General)
spellingShingle T Technology (General)
Yusof, Rubiyah
Ahmad, Azlin
Mohd. Khairuddin, Anis Salwa
Khairuddin, Uswah
Nik Azmi, Nik Mohamad Aizuddin
Rosli, Nenny Ruthfalydia
Transfer learning approach in automatic tropical wood recognition system
description Automatic recognition of tropical wood species is a very challenging task due to the lack of discriminative features among intra wood species and very discriminative features among inter class species. While many conventional pattern recognition algorithms have been implemented and proven to solve wood image classification with 100% accuracy, when using deep learning however, the classification accuracy drops tremendously to only 36.3% due to small number of training samples. Deep learning requires large number of samples in order to work well, unfortunately, wood samples provided by the national forest institute are limited. In this paper, we explore the use of transfer learning in deep neural network for the classification of tropical wood species based on image analysis. Several model of deep learning techniques are tested and results have shown that the classification performance after transfer learning was added reaches 100% accuracy.
format Book Section
author Yusof, Rubiyah
Ahmad, Azlin
Mohd. Khairuddin, Anis Salwa
Khairuddin, Uswah
Nik Azmi, Nik Mohamad Aizuddin
Rosli, Nenny Ruthfalydia
author_facet Yusof, Rubiyah
Ahmad, Azlin
Mohd. Khairuddin, Anis Salwa
Khairuddin, Uswah
Nik Azmi, Nik Mohamad Aizuddin
Rosli, Nenny Ruthfalydia
author_sort Yusof, Rubiyah
title Transfer learning approach in automatic tropical wood recognition system
title_short Transfer learning approach in automatic tropical wood recognition system
title_full Transfer learning approach in automatic tropical wood recognition system
title_fullStr Transfer learning approach in automatic tropical wood recognition system
title_full_unstemmed Transfer learning approach in automatic tropical wood recognition system
title_sort transfer learning approach in automatic tropical wood recognition system
publisher Springer
publishDate 2020
url http://eprints.utm.my/id/eprint/92239/
http://dx.doi.org/10.1088/1757-899X/849/1/012039
_version_ 1712285068444041216
score 13.211869

Similar Items