Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks
碩士 === 國立臺灣大學 === 生物產業機電工程學研究所 === 107 === Tree and seedling adulteration has becoming an issue in plant cultivation. Cinnamomum osmophloeum (Lauraceae) is an evergreen plant that yields cinnamaldehyde compound and has high economic value. Although morphologically resembling C. osmophloeum, two othe...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/e55e9v |
id |
ndltd-TW-107NTU05415008 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107NTU054150082019-06-27T05:48:12Z http://ndltd.ncl.edu.tw/handle/e55e9v Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks 利用深度卷積類神經網路辨識形態相似的樟屬(樟科)物種 Hao-Wen Yang 楊皓文 碩士 國立臺灣大學 生物產業機電工程學研究所 107 Tree and seedling adulteration has becoming an issue in plant cultivation. Cinnamomum osmophloeum (Lauraceae) is an evergreen plant that yields cinnamaldehyde compound and has high economic value. Although morphologically resembling C. osmophloeum, two other species, C. burmannii and C. insulari-montanum, do not produce cinnamaldehyde. Adulteration of C. burmannii using C. osmophloeum has been reported in Taiwan. Yet, even for experts, it is challenging to discriminate the three species from their appearance due to their high degree of similarity. This brings economic loss to forest farmers owing to the value discrepancy between the species. This study proposed to identify the three Cinnamomum species using leaf images and deep learning approaches. In the study, leaf images of the three species were acquired from two camps using flatbed scanners. Deep convolutional neural network (CNN) classifiers based on VGG16, Inception-V3, and NASNet models were then developed using the leaf images collected from one garden as the training samples. The result showed that the developed deep CNN classifiers reached a test accuracy of at least 0.87 on the images collected from the other garden. The developed CNN classifiers also outperformed support vector machine classifiers. Yan-Fu Kuo 郭彥甫 2018 學位論文 ; thesis 26 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣大學 === 生物產業機電工程學研究所 === 107 === Tree and seedling adulteration has becoming an issue in plant cultivation. Cinnamomum osmophloeum (Lauraceae) is an evergreen plant that yields cinnamaldehyde compound and has high economic value. Although morphologically resembling C. osmophloeum, two other species, C. burmannii and C. insulari-montanum, do not produce cinnamaldehyde. Adulteration of C. burmannii using C. osmophloeum has been reported in Taiwan. Yet, even for experts, it is challenging to discriminate the three species from their appearance due to their high degree of similarity. This brings economic loss to forest farmers owing to the value discrepancy between the species. This study proposed to identify the three Cinnamomum species using leaf images and deep learning approaches. In the study, leaf images of the three species were acquired from two camps using flatbed scanners. Deep convolutional neural network (CNN) classifiers based on VGG16, Inception-V3, and NASNet models were then developed using the leaf images collected from one garden as the training samples. The result showed that the developed deep CNN classifiers reached a test accuracy of at least 0.87 on the images collected from the other garden. The developed CNN classifiers also outperformed support vector machine classifiers.
|
author2 |
Yan-Fu Kuo |
author_facet |
Yan-Fu Kuo Hao-Wen Yang 楊皓文 |
author |
Hao-Wen Yang 楊皓文 |
spellingShingle |
Hao-Wen Yang 楊皓文 Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks |
author_sort |
Hao-Wen Yang |
title |
Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks |
title_short |
Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks |
title_full |
Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks |
title_fullStr |
Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks |
title_full_unstemmed |
Discriminating morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks |
title_sort |
discriminating morphologically similar species in genus cinnamomum (lauraceae) using deep convolutional neural networks |
publishDate |
2018 |
url |
http://ndltd.ncl.edu.tw/handle/e55e9v |
work_keys_str_mv |
AT haowenyang discriminatingmorphologicallysimilarspeciesingenuscinnamomumlauraceaeusingdeepconvolutionalneuralnetworks AT yánghàowén discriminatingmorphologicallysimilarspeciesingenuscinnamomumlauraceaeusingdeepconvolutionalneuralnetworks AT haowenyang lìyòngshēndùjuǎnjīlèishénjīngwǎnglùbiànshíxíngtàixiāngshìdezhāngshǔzhāngkēwùzhǒng AT yánghàowén lìyòngshēndùjuǎnjīlèishénjīngwǎnglùbiànshíxíngtàixiāngshìdezhāngshǔzhāngkēwùzhǒng |
_version_ |
1719214048144261120 |