Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation
Herbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines since ancient times. Malaysia has hundreds of plant species; herb detection may be difficult due to the variety of herb speci...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2023-03-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | http://ijain.org/index.php/IJAIN/article/view/1076 |
| _version_ | 1827973861275074560 |
|---|---|
| author | Noor Aini Mohd Roslan Norizan Mat Diah Zaidah Ibrahim Yuda Munarko Agus Eko Minarno |
| author_facet | Noor Aini Mohd Roslan Norizan Mat Diah Zaidah Ibrahim Yuda Munarko Agus Eko Minarno |
| author_sort | Noor Aini Mohd Roslan |
| collection | DOAJ |
| description | Herbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines since ancient times. Malaysia has hundreds of plant species; herb detection may be difficult due to the variety of herb species and their shape and color similarities. Furthermore, there is a scarcity of support datasets for detecting these plants. The main objective of this paper is to investigate the performance of convolutional neural network (CNN) on Malaysian medicinal herbs datasets, real data and augmented data. Malaysian medical herbs data were obtained from Taman Herba Pulau Pinang, Malaysia, and ten kinds of native herbs were chosen. Both datasets were evaluated using the CNN model developed throughout the research. Overall, herbs real data obtained an average accuracy of 75%, whereas herbs augmented data achieved an average accuracy of 88%. Based on these findings, herbs augmented data surpassed herbs actual data in terms of accuracy after undergoing the augmentation technique. |
| first_indexed | 2024-04-09T19:45:42Z |
| format | Article |
| id | doaj.art-a5cadbdaa1104c2b96431e85064b92da |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-04-09T19:45:42Z |
| publishDate | 2023-03-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-a5cadbdaa1104c2b96431e85064b92da2023-04-03T19:52:33ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612023-03-019113614710.26555/ijain.v9i1.1076235Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentationNoor Aini Mohd Roslan0Norizan Mat Diah1Zaidah Ibrahim2Yuda Munarko3Agus Eko Minarno4School of Computing Sciences, College of Computing, Informatics and Media, Universiti Teknologi MARASchool of Computing Sciences, College of Computing, Informatics and Media, Universiti Teknologi MARASchool of Computing Sciences, College of Computing, Informatics and Media, Universiti Teknologi MARAInformatics Department, Universitas Muhammadiyah MalangInformatics Department, Universitas Muhammadiyah MalangHerbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines since ancient times. Malaysia has hundreds of plant species; herb detection may be difficult due to the variety of herb species and their shape and color similarities. Furthermore, there is a scarcity of support datasets for detecting these plants. The main objective of this paper is to investigate the performance of convolutional neural network (CNN) on Malaysian medicinal herbs datasets, real data and augmented data. Malaysian medical herbs data were obtained from Taman Herba Pulau Pinang, Malaysia, and ten kinds of native herbs were chosen. Both datasets were evaluated using the CNN model developed throughout the research. Overall, herbs real data obtained an average accuracy of 75%, whereas herbs augmented data achieved an average accuracy of 88%. Based on these findings, herbs augmented data surpassed herbs actual data in terms of accuracy after undergoing the augmentation technique.http://ijain.org/index.php/IJAIN/article/view/1076convolutional neural network (cnn)deep learningmalaysian medicinal herbsdata augmentation |
| spellingShingle | Noor Aini Mohd Roslan Norizan Mat Diah Zaidah Ibrahim Yuda Munarko Agus Eko Minarno Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation IJAIN (International Journal of Advances in Intelligent Informatics) convolutional neural network (cnn) deep learning malaysian medicinal herbs data augmentation |
| title | Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation |
| title_full | Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation |
| title_fullStr | Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation |
| title_full_unstemmed | Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation |
| title_short | Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation |
| title_sort | automatic plant recognition using convolutional neural network on malaysian medicinal herbs the value of data augmentation |
| topic | convolutional neural network (cnn) deep learning malaysian medicinal herbs data augmentation |
| url | http://ijain.org/index.php/IJAIN/article/view/1076 |
| work_keys_str_mv | AT noorainimohdroslan automaticplantrecognitionusingconvolutionalneuralnetworkonmalaysianmedicinalherbsthevalueofdataaugmentation AT norizanmatdiah automaticplantrecognitionusingconvolutionalneuralnetworkonmalaysianmedicinalherbsthevalueofdataaugmentation AT zaidahibrahim automaticplantrecognitionusingconvolutionalneuralnetworkonmalaysianmedicinalherbsthevalueofdataaugmentation AT yudamunarko automaticplantrecognitionusingconvolutionalneuralnetworkonmalaysianmedicinalherbsthevalueofdataaugmentation AT agusekominarno automaticplantrecognitionusingconvolutionalneuralnetworkonmalaysianmedicinalherbsthevalueofdataaugmentation |