Deep Learning for Plant Species Classification using Leaf Vein Morphometric
An automated plant species identification system could help botanists and layman in identifying plant species rapidly. Deep learning is robust for feature extraction as it is superior in providing deeper information of images. In this research, a new CNN-based method named D-Leaf was proposed. The l...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Published: |
Institute of Electrical and Electronics Engineers
2018
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/24834/ https://doi.org/10.1109/TCBB.2018.2848653 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.24834 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.248342020-06-16T01:13:27Z http://eprints.um.edu.my/24834/ Deep Learning for Plant Species Classification using Leaf Vein Morphometric Tan, Jing Wei Chang, Siow Wee Kareem, Sameem Abdul Yap, Hwa Jen Yong, Kien Thai Q Science (General) QA75 Electronic computers. Computer science QH Natural history TJ Mechanical engineering and machinery An automated plant species identification system could help botanists and layman in identifying plant species rapidly. Deep learning is robust for feature extraction as it is superior in providing deeper information of images. In this research, a new CNN-based method named D-Leaf was proposed. The leaf images were pre-processed and the features were extracted by using three different Convolutional Neural Network (CNN) models namely pre-trained AlexNet, fine-tuned AlexNet, and D-Leaf. These features were then classified by using five machine learning techniques, namely, Support Vector Machine (SVM), Artificial Neural Network (ANN), k-Nearest-Neighbor (k-NN), Naïve-Bayes (NB), and CNN. A conventional morphometric method computed the morphological measurements based on the Sobel segmented veins was employed for benchmarking purposes. The D-Leaf model achieved a comparable testing accuracy of 94.88 percent as compared to AlexNet (93.26 percent) and fine-tuned AlexNet (95.54 percent) models. In addition, CNN models performed better than the traditional morphometric measurements (66.55 percent). The features extracted from the CNN are found to be fitted well with the ANN classifier. D-Leaf can be an effective automated system for plant species identification as shown by the experimental results. © 2004-2012 IEEE. Institute of Electrical and Electronics Engineers 2018 Article PeerReviewed Tan, Jing Wei and Chang, Siow Wee and Kareem, Sameem Abdul and Yap, Hwa Jen and Yong, Kien Thai (2018) Deep Learning for Plant Species Classification using Leaf Vein Morphometric. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 17 (1). pp. 82-90. ISSN 1545-5963 https://doi.org/10.1109/TCBB.2018.2848653 doi:10.1109/TCBB.2018.2848653 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
Q Science (General) QA75 Electronic computers. Computer science QH Natural history TJ Mechanical engineering and machinery |
spellingShingle |
Q Science (General) QA75 Electronic computers. Computer science QH Natural history TJ Mechanical engineering and machinery Tan, Jing Wei Chang, Siow Wee Kareem, Sameem Abdul Yap, Hwa Jen Yong, Kien Thai Deep Learning for Plant Species Classification using Leaf Vein Morphometric |
description |
An automated plant species identification system could help botanists and layman in identifying plant species rapidly. Deep learning is robust for feature extraction as it is superior in providing deeper information of images. In this research, a new CNN-based method named D-Leaf was proposed. The leaf images were pre-processed and the features were extracted by using three different Convolutional Neural Network (CNN) models namely pre-trained AlexNet, fine-tuned AlexNet, and D-Leaf. These features were then classified by using five machine learning techniques, namely, Support Vector Machine (SVM), Artificial Neural Network (ANN), k-Nearest-Neighbor (k-NN), Naïve-Bayes (NB), and CNN. A conventional morphometric method computed the morphological measurements based on the Sobel segmented veins was employed for benchmarking purposes. The D-Leaf model achieved a comparable testing accuracy of 94.88 percent as compared to AlexNet (93.26 percent) and fine-tuned AlexNet (95.54 percent) models. In addition, CNN models performed better than the traditional morphometric measurements (66.55 percent). The features extracted from the CNN are found to be fitted well with the ANN classifier. D-Leaf can be an effective automated system for plant species identification as shown by the experimental results. © 2004-2012 IEEE. |
format |
Article |
author |
Tan, Jing Wei Chang, Siow Wee Kareem, Sameem Abdul Yap, Hwa Jen Yong, Kien Thai |
author_facet |
Tan, Jing Wei Chang, Siow Wee Kareem, Sameem Abdul Yap, Hwa Jen Yong, Kien Thai |
author_sort |
Tan, Jing Wei |
title |
Deep Learning for Plant Species Classification using Leaf Vein Morphometric |
title_short |
Deep Learning for Plant Species Classification using Leaf Vein Morphometric |
title_full |
Deep Learning for Plant Species Classification using Leaf Vein Morphometric |
title_fullStr |
Deep Learning for Plant Species Classification using Leaf Vein Morphometric |
title_full_unstemmed |
Deep Learning for Plant Species Classification using Leaf Vein Morphometric |
title_sort |
deep learning for plant species classification using leaf vein morphometric |
publisher |
Institute of Electrical and Electronics Engineers |
publishDate |
2018 |
url |
http://eprints.um.edu.my/24834/ https://doi.org/10.1109/TCBB.2018.2848653 |
_version_ |
1674066735841411072 |
score |
13.18916 |