Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species
This paper presents a machine learning approach to automatically classifying post-harvest vegetal species. Color images of vegetal species were applied to convolutional neural networks (CNNs) and support vector machine (SVM) classifiers. We focused on okra as the target vegetal species and classifie...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | AgriEngineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/5/2/63 |
| _version_ | 1797596538049921024 |
|---|---|
| author | Papa Moussa Diop Naoki Oshiro Morikazu Nakamura Jin Takamoto Yuji Nakamura |
| author_facet | Papa Moussa Diop Naoki Oshiro Morikazu Nakamura Jin Takamoto Yuji Nakamura |
| author_sort | Papa Moussa Diop |
| collection | DOAJ |
| description | This paper presents a machine learning approach to automatically classifying post-harvest vegetal species. Color images of vegetal species were applied to convolutional neural networks (CNNs) and support vector machine (SVM) classifiers. We focused on okra as the target vegetal species and classified it into two quality types. However, our approach could also be applied to other species. The machine learning solution consists of several components, and each design process and its combinations are essential for classification quality. Therefore, we carefully investigated their effects on classification accuracy. Through our experimental evaluation, we confirmed the following: (1) in color space selection, HLG (hue, lightness, and green) and HSL (hue, saturation, and lightness) are essential for vegetal species; (2) suitable preprocessing techniques are required owing to the complexity of the data and noise load; and (3) the diversity extension of learning image data by mixing different datasets obtained under different conditions is quite effective in reducing the overfitting possibility. The results of this study will assist AI practitioners in the design and development of post-harvest classifications based on machine learning. |
| first_indexed | 2024-03-11T02:52:52Z |
| format | Article |
| id | doaj.art-77330a7dc2ee43cd803a96e652b8bb7e |
| institution | Directory Open Access Journal |
| issn | 2624-7402 |
| language | English |
| last_indexed | 2024-03-11T02:52:52Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AgriEngineering |
| spelling | doaj.art-77330a7dc2ee43cd803a96e652b8bb7e2023-11-18T08:53:00ZengMDPI AGAgriEngineering2624-74022023-06-01521005101910.3390/agriengineering5020063Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal SpeciesPapa Moussa Diop0Naoki Oshiro1Morikazu Nakamura2Jin Takamoto3Yuji Nakamura4Graduate School of Engineering and Science, University of the Ryukyus, Okinawa 903-0213, JapanFaculty of Engineering, University of the Ryukyus, Okinawa 903-0213, JapanFaculty of Engineering, University of the Ryukyus, Okinawa 903-0213, JapanMedia Transport Corporation, Nakagami-gun, Nakagusuku, Okinawa 901-2423, JapanMedia Transport Corporation, Nakagami-gun, Nakagusuku, Okinawa 901-2423, JapanThis paper presents a machine learning approach to automatically classifying post-harvest vegetal species. Color images of vegetal species were applied to convolutional neural networks (CNNs) and support vector machine (SVM) classifiers. We focused on okra as the target vegetal species and classified it into two quality types. However, our approach could also be applied to other species. The machine learning solution consists of several components, and each design process and its combinations are essential for classification quality. Therefore, we carefully investigated their effects on classification accuracy. Through our experimental evaluation, we confirmed the following: (1) in color space selection, HLG (hue, lightness, and green) and HSL (hue, saturation, and lightness) are essential for vegetal species; (2) suitable preprocessing techniques are required owing to the complexity of the data and noise load; and (3) the diversity extension of learning image data by mixing different datasets obtained under different conditions is quite effective in reducing the overfitting possibility. The results of this study will assist AI practitioners in the design and development of post-harvest classifications based on machine learning.https://www.mdpi.com/2624-7402/5/2/63vegetal classificationmachine learningsupport vector machine (SVM)convolutional neural network (CNN)color space |
| spellingShingle | Papa Moussa Diop Naoki Oshiro Morikazu Nakamura Jin Takamoto Yuji Nakamura Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species AgriEngineering vegetal classification machine learning support vector machine (SVM) convolutional neural network (CNN) color space |
| title | Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species |
| title_full | Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species |
| title_fullStr | Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species |
| title_full_unstemmed | Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species |
| title_short | Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species |
| title_sort | design of machine learning solutions to post harvest classification of vegetal species |
| topic | vegetal classification machine learning support vector machine (SVM) convolutional neural network (CNN) color space |
| url | https://www.mdpi.com/2624-7402/5/2/63 |
| work_keys_str_mv | AT papamoussadiop designofmachinelearningsolutionstopostharvestclassificationofvegetalspecies AT naokioshiro designofmachinelearningsolutionstopostharvestclassificationofvegetalspecies AT morikazunakamura designofmachinelearningsolutionstopostharvestclassificationofvegetalspecies AT jintakamoto designofmachinelearningsolutionstopostharvestclassificationofvegetalspecies AT yujinakamura designofmachinelearningsolutionstopostharvestclassificationofvegetalspecies |