Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment
This paper examines a deep convolutional neural network (Deep CNN) for plant recognition in the natural environment. The primary objective was to compare 4 CNN architectures including LeNet-5, AlexNet, GoogLeNet, and VGGNet on three plant datasets; PNE, 102 Flower, and Folio. The images in the PNE a...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Thai |
| Published: |
Mahasarakham University
2019-04-01
|
| Series: | Warasan Witthayasat Lae Theknoloyi Mahawitthayalai Mahasarakham |
| Subjects: | |
| Online Access: | http://journal.msu.ac.th/upload/articles/article2449_80536.pdf |
| _version_ | 1818379923537002496 |
|---|---|
| author | Jakkarin Sanuksan |
| author_facet | Jakkarin Sanuksan |
| author_sort | Jakkarin Sanuksan |
| collection | DOAJ |
| description | This paper examines a deep convolutional neural network (Deep CNN) for plant recognition in the natural environment. The primary objective was to compare 4 CNN architectures including LeNet-5, AlexNet, GoogLeNet, and VGGNet on three plant datasets; PNE, 102 Flower, and Folio. The images in the PNE and 102 Flower dataset include a complicated background because they were taken in a natural environment. On the other hand, the images in the Folid dataset are only leaf images that were taken in a laboratory environment using a white background. The comparison of deep CNN using GoogLeNet and VGGNet Architecture show that GoogLeNet outperformed while working on the PNE and 102 Flower dataset when using a training time with iterations of 10,000 epochs. GoogLeNet also faster than the VGGNet architecture. However, the experiment showed that the VGGNet architecture outperforms
the other CNN architectures on the Folio dataset and used only 1,000 epochs for training. In our experiment, we can create a model from the deep CNN using GoogleNet architecture, and this is because it showed better results with the plant images that were taken in the natural environment. |
| first_indexed | 2024-12-14T02:10:30Z |
| format | Article |
| id | doaj.art-b84b5832d4834559b00cd40fa30f02c8 |
| institution | Directory Open Access Journal |
| issn | 1686-9664 |
| language | Thai |
| last_indexed | 2024-12-14T02:10:30Z |
| publishDate | 2019-04-01 |
| publisher | Mahasarakham University |
| record_format | Article |
| series | Warasan Witthayasat Lae Theknoloyi Mahawitthayalai Mahasarakham |
| spelling | doaj.art-b84b5832d4834559b00cd40fa30f02c82022-12-21T23:20:47ZthaMahasarakham UniversityWarasan Witthayasat Lae Theknoloyi Mahawitthayalai Mahasarakham1686-96642019-04-01382113124Deep Convolutional Neural Networks for Plant Recognition in the Natural EnvironmentJakkarin Sanuksan0Master Student, Multi-agent Intelligent Simulation Laboratory (MISL), Department of Information Technology Faculty of Informatics, Mahasarakham University, Maha Sarakham 44150, ThailandThis paper examines a deep convolutional neural network (Deep CNN) for plant recognition in the natural environment. The primary objective was to compare 4 CNN architectures including LeNet-5, AlexNet, GoogLeNet, and VGGNet on three plant datasets; PNE, 102 Flower, and Folio. The images in the PNE and 102 Flower dataset include a complicated background because they were taken in a natural environment. On the other hand, the images in the Folid dataset are only leaf images that were taken in a laboratory environment using a white background. The comparison of deep CNN using GoogLeNet and VGGNet Architecture show that GoogLeNet outperformed while working on the PNE and 102 Flower dataset when using a training time with iterations of 10,000 epochs. GoogLeNet also faster than the VGGNet architecture. However, the experiment showed that the VGGNet architecture outperforms the other CNN architectures on the Folio dataset and used only 1,000 epochs for training. In our experiment, we can create a model from the deep CNN using GoogleNet architecture, and this is because it showed better results with the plant images that were taken in the natural environment.http://journal.msu.ac.th/upload/articles/article2449_80536.pdfplant recognitiondeep learningdeep convolutional neural networkalexnet architecturegooglenet architecturevggnet architecture |
| spellingShingle | Jakkarin Sanuksan Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment Warasan Witthayasat Lae Theknoloyi Mahawitthayalai Mahasarakham plant recognition deep learning deep convolutional neural network alexnet architecture googlenet architecture vggnet architecture |
| title | Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment |
| title_full | Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment |
| title_fullStr | Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment |
| title_full_unstemmed | Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment |
| title_short | Deep Convolutional Neural Networks for Plant Recognition in the Natural Environment |
| title_sort | deep convolutional neural networks for plant recognition in the natural environment |
| topic | plant recognition deep learning deep convolutional neural network alexnet architecture googlenet architecture vggnet architecture |
| url | http://journal.msu.ac.th/upload/articles/article2449_80536.pdf |
| work_keys_str_mv | AT jakkarinsanuksan deepconvolutionalneuralnetworksforplantrecognitioninthenaturalenvironment |