Herbal plant recognition using deep convolutional neural network

This paper investigates the application of deep Convolutional Neural Network (CNN) for herbal plant recognition through leaf identification. Traditional plant identification is often time-consuming due to varieties as well as similarities possessed within the plant species. This study shows that a d...

Full description

Bibliographic Details
Published in:Bulletin of Electrical Engineering and Informatics
Main Author: Zin I.A.M.; Ibrahim Z.; Isa D.; Aliman S.; Sabri N.; Mangshor N.N.A.
Format: Article
Language:English
Published: Institute of Advanced Engineering and Science 2020
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087114927&doi=10.11591%2feei.v9i5.2250&partnerID=40&md5=927c5ca7fb5af08a4c997361a3292c1f
id 2-s2.0-85087114927
spelling 2-s2.0-85087114927
Zin I.A.M.; Ibrahim Z.; Isa D.; Aliman S.; Sabri N.; Mangshor N.N.A.
Herbal plant recognition using deep convolutional neural network
2020
Bulletin of Electrical Engineering and Informatics
9
5
10.11591/eei.v9i5.2250
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087114927&doi=10.11591%2feei.v9i5.2250&partnerID=40&md5=927c5ca7fb5af08a4c997361a3292c1f
This paper investigates the application of deep Convolutional Neural Network (CNN) for herbal plant recognition through leaf identification. Traditional plant identification is often time-consuming due to varieties as well as similarities possessed within the plant species. This study shows that a deep CNN model can be created and enhanced using multiple parameters to boost recognition accuracy performance. This study also shows the significant effects of the multi-layer model on small sample sizes to achieve reasonable performance. Furthermore, data augmentation provides more significant benefits on the overall performance. Simple augmentations such as resize, flip and rotate will increase accuracy significantly by creating invariance and preventing the model from learning irrelevant features. A new dataset of the leaves of various herbal plants found in Malaysia has been constructed and the experimental results achieved 99% accuracy. © 2020, Institute of Advanced Engineering and Science. All rights reserved.
Institute of Advanced Engineering and Science
20893191
English
Article
All Open Access; Gold Open Access
author Zin I.A.M.; Ibrahim Z.; Isa D.; Aliman S.; Sabri N.; Mangshor N.N.A.
spellingShingle Zin I.A.M.; Ibrahim Z.; Isa D.; Aliman S.; Sabri N.; Mangshor N.N.A.
Herbal plant recognition using deep convolutional neural network
author_facet Zin I.A.M.; Ibrahim Z.; Isa D.; Aliman S.; Sabri N.; Mangshor N.N.A.
author_sort Zin I.A.M.; Ibrahim Z.; Isa D.; Aliman S.; Sabri N.; Mangshor N.N.A.
title Herbal plant recognition using deep convolutional neural network
title_short Herbal plant recognition using deep convolutional neural network
title_full Herbal plant recognition using deep convolutional neural network
title_fullStr Herbal plant recognition using deep convolutional neural network
title_full_unstemmed Herbal plant recognition using deep convolutional neural network
title_sort Herbal plant recognition using deep convolutional neural network
publishDate 2020
container_title Bulletin of Electrical Engineering and Informatics
container_volume 9
container_issue 5
doi_str_mv 10.11591/eei.v9i5.2250
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087114927&doi=10.11591%2feei.v9i5.2250&partnerID=40&md5=927c5ca7fb5af08a4c997361a3292c1f
description This paper investigates the application of deep Convolutional Neural Network (CNN) for herbal plant recognition through leaf identification. Traditional plant identification is often time-consuming due to varieties as well as similarities possessed within the plant species. This study shows that a deep CNN model can be created and enhanced using multiple parameters to boost recognition accuracy performance. This study also shows the significant effects of the multi-layer model on small sample sizes to achieve reasonable performance. Furthermore, data augmentation provides more significant benefits on the overall performance. Simple augmentations such as resize, flip and rotate will increase accuracy significantly by creating invariance and preventing the model from learning irrelevant features. A new dataset of the leaves of various herbal plants found in Malaysia has been constructed and the experimental results achieved 99% accuracy. © 2020, Institute of Advanced Engineering and Science. All rights reserved.
publisher Institute of Advanced Engineering and Science
issn 20893191
language English
format Article
accesstype All Open Access; Gold Open Access
record_format scopus
collection Scopus
_version_ 1809677895543554048