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...

Full description

Saved in:
Bibliographic Details
Main Authors: Damrongvudhi Onwimol, Pongsan Chakranon, Kris Wonggasem, Papis Wongchaisuwat
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