Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging
Hyperspectral imaging was employed to capture spectral information from entire trays of hemp seeds. Individual seed spectral data was extracted using a region-of-interest analysis, isolating each seed for detailed examination. To simplify the analysis and reduce computational complexity, a subset of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Journal of Agriculture and Food Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666154325002078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850226028308332544 |
|---|---|
| author | Damrongvudhi Onwimol Pongsan Chakranon Kris Wonggasem Papis Wongchaisuwat |
| author_facet | Damrongvudhi Onwimol Pongsan Chakranon Kris Wonggasem Papis Wongchaisuwat |
| author_sort | Damrongvudhi Onwimol |
| collection | DOAJ |
| description | Hyperspectral imaging was employed to capture spectral information from entire trays of hemp seeds. Individual seed spectral data was extracted using a region-of-interest analysis, isolating each seed for detailed examination. To simplify the analysis and reduce computational complexity, a subset of key spectral wavelengths was selected using a successive projection algorithm. Deep learning models were trained on these selected wavelengths to directly learn patterns from the raw spectral data. The performance of these deep learning models was compared to traditional machine learning approaches. Particularly, an EfficientNetB0 convolutional neural networks achieved the most impressive results, demonstrating a high sensitivity of 98.85, a specificity of 99.22, and a Matthews correlation coefficient of 0.98. It indicated its ability to accurately distinguish between high-vigor and low-vigor hemp seeds. Our findings demonstrated the potential of data-driven models trained on hyperspectral imaging data for non-destructive assessment of hemp seed vigor. This approach offers an advantage over traditional methods, which often involve destructive testing or time-consuming manual evaluation. By enabling rapid and objective seed selection, this technology can improve the efficiency of hemp seed production and ultimately lead to higher crop yields. This innovative approach has the potential to revolutionize the agricultural industry by providing a powerful tool for assessing seed quality and optimizing crop production. |
| format | Article |
| id | doaj-art-021b7b5f6fcc41fc8c80beb880a8e30c |
| institution | OA Journals |
| issn | 2666-1543 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Agriculture and Food Research |
| spelling | doaj-art-021b7b5f6fcc41fc8c80beb880a8e30c2025-08-20T02:05:11ZengElsevierJournal of Agriculture and Food Research2666-15432025-06-012110183610.1016/j.jafr.2025.101836Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imagingDamrongvudhi Onwimol0Pongsan Chakranon1Kris Wonggasem2Papis Wongchaisuwat3Department of Agronomy, Faculty of Agriculture, Kasetsart University, Bangkok, 10900, ThailandDepartment of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, ThailandDepartment of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, ThailandDepartment of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, Thailand; Corresponding author.Hyperspectral imaging was employed to capture spectral information from entire trays of hemp seeds. Individual seed spectral data was extracted using a region-of-interest analysis, isolating each seed for detailed examination. To simplify the analysis and reduce computational complexity, a subset of key spectral wavelengths was selected using a successive projection algorithm. Deep learning models were trained on these selected wavelengths to directly learn patterns from the raw spectral data. The performance of these deep learning models was compared to traditional machine learning approaches. Particularly, an EfficientNetB0 convolutional neural networks achieved the most impressive results, demonstrating a high sensitivity of 98.85, a specificity of 99.22, and a Matthews correlation coefficient of 0.98. It indicated its ability to accurately distinguish between high-vigor and low-vigor hemp seeds. Our findings demonstrated the potential of data-driven models trained on hyperspectral imaging data for non-destructive assessment of hemp seed vigor. This approach offers an advantage over traditional methods, which often involve destructive testing or time-consuming manual evaluation. By enabling rapid and objective seed selection, this technology can improve the efficiency of hemp seed production and ultimately lead to higher crop yields. This innovative approach has the potential to revolutionize the agricultural industry by providing a powerful tool for assessing seed quality and optimizing crop production.http://www.sciencedirect.com/science/article/pii/S2666154325002078Hemp seed vigorHyperspectral imaging analysisMachine learningDeep learningWavelength selection |
| spellingShingle | Damrongvudhi Onwimol Pongsan Chakranon Kris Wonggasem Papis Wongchaisuwat Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging Journal of Agriculture and Food Research Hemp seed vigor Hyperspectral imaging analysis Machine learning Deep learning Wavelength selection |
| title | Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging |
| title_full | Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging |
| title_fullStr | Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging |
| title_full_unstemmed | Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging |
| title_short | Non-destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging |
| title_sort | non destructive assessment of hemp seed vigor using machine learning and deep learning models with hyperspectral imaging |
| topic | Hemp seed vigor Hyperspectral imaging analysis Machine learning Deep learning Wavelength selection |
| url | http://www.sciencedirect.com/science/article/pii/S2666154325002078 |
| work_keys_str_mv | AT damrongvudhionwimol nondestructiveassessmentofhempseedvigorusingmachinelearninganddeeplearningmodelswithhyperspectralimaging AT pongsanchakranon nondestructiveassessmentofhempseedvigorusingmachinelearninganddeeplearningmodelswithhyperspectralimaging AT kriswonggasem nondestructiveassessmentofhempseedvigorusingmachinelearninganddeeplearningmodelswithhyperspectralimaging AT papiswongchaisuwat nondestructiveassessmentofhempseedvigorusingmachinelearninganddeeplearningmodelswithhyperspectralimaging |