Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques
Utilizing conventional methods to assess the seed quality is typically destructive and time-consuming. This research aimed to develop a robust and efficient framework for classifying maize seed vigor using hyperspectral imaging and deep learning. This study involved acquiring hyperspectral imaging d...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525000541 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864261129011200 |
|---|---|
| author | Papis Wongchaisuwat Pongsan Chakranon Achitpon Yinpin Damrongvudhi Onwimol Kris Wonggasem |
| author_facet | Papis Wongchaisuwat Pongsan Chakranon Achitpon Yinpin Damrongvudhi Onwimol Kris Wonggasem |
| author_sort | Papis Wongchaisuwat |
| collection | DOAJ |
| description | Utilizing conventional methods to assess the seed quality is typically destructive and time-consuming. This research aimed to develop a robust and efficient framework for classifying maize seed vigor using hyperspectral imaging and deep learning. This study involved acquiring hyperspectral imaging data, preprocessing images, and designing convolutional neural network architectures. We explored various network structures, including one-dimensional (1DCNN), two-dimensional (2DCNN), and three-dimensional convolutional neural networks (3DCNN). The impact of wavelength selection on model performance using the successive projection analysis was also explored. The combination of wavelength selection and careful CNN architecture choice significantly contributed to the proposed model's exceptional performance. The 3DCNN model utilizing the full spectral dataset achieved outstanding results, with 100 % sensitivity, 99.89 % specificity, and a Matthews correlation coefficient of 0.9966. Our findings demonstrated the potential of this rapid and non-destructive seed vigor assessment as a practical solution for real-world seed quality control in the agricultural industry. |
| format | Article |
| id | doaj-art-9f3f7db852e3455794b8e48541e5e47b |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-9f3f7db852e3455794b8e48541e5e47b2025-02-09T05:01:40ZengElsevierSmart Agricultural Technology2772-37552025-03-0110100820Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniquesPapis Wongchaisuwat0Pongsan Chakranon1Achitpon Yinpin2Damrongvudhi Onwimol3Kris Wonggasem4Department of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, ThailandDepartment of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, ThailandDepartment of Agronomy, Faculty of Agriculture, Kasetsart University, Bangkok, 10900, ThailandDepartment of Agronomy, Faculty of Agriculture, Kasetsart University, Bangkok, 10900, ThailandDepartment of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, Thailand; Corresponding author: Department of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok, 10900, Thailand.Utilizing conventional methods to assess the seed quality is typically destructive and time-consuming. This research aimed to develop a robust and efficient framework for classifying maize seed vigor using hyperspectral imaging and deep learning. This study involved acquiring hyperspectral imaging data, preprocessing images, and designing convolutional neural network architectures. We explored various network structures, including one-dimensional (1DCNN), two-dimensional (2DCNN), and three-dimensional convolutional neural networks (3DCNN). The impact of wavelength selection on model performance using the successive projection analysis was also explored. The combination of wavelength selection and careful CNN architecture choice significantly contributed to the proposed model's exceptional performance. The 3DCNN model utilizing the full spectral dataset achieved outstanding results, with 100 % sensitivity, 99.89 % specificity, and a Matthews correlation coefficient of 0.9966. Our findings demonstrated the potential of this rapid and non-destructive seed vigor assessment as a practical solution for real-world seed quality control in the agricultural industry.http://www.sciencedirect.com/science/article/pii/S2772375525000541Seed vigorZea maysHyperspectral imagingDeep learningNon-destructive sorter |
| spellingShingle | Papis Wongchaisuwat Pongsan Chakranon Achitpon Yinpin Damrongvudhi Onwimol Kris Wonggasem Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques Smart Agricultural Technology Seed vigor Zea mays Hyperspectral imaging Deep learning Non-destructive sorter |
| title | Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques |
| title_full | Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques |
| title_fullStr | Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques |
| title_full_unstemmed | Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques |
| title_short | Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques |
| title_sort | rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques |
| topic | Seed vigor Zea mays Hyperspectral imaging Deep learning Non-destructive sorter |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525000541 |
| work_keys_str_mv | AT papiswongchaisuwat rapidmaizeseedvigorclassificationusingdeeplearningandhyperspectralimagingtechniques AT pongsanchakranon rapidmaizeseedvigorclassificationusingdeeplearningandhyperspectralimagingtechniques AT achitponyinpin rapidmaizeseedvigorclassificationusingdeeplearningandhyperspectralimagingtechniques AT damrongvudhionwimol rapidmaizeseedvigorclassificationusingdeeplearningandhyperspectralimagingtechniques AT kriswonggasem rapidmaizeseedvigorclassificationusingdeeplearningandhyperspectralimagingtechniques |