Detection of insect-damaged sunflower seeds using near-infrared hyperspectral imaging and machine learning

Authors: MENSAH, BRIGHT - North Dakota State University; Prasifka, Jarrad; Hulke, Brent; MONONO, EWUMBUA - North Dakota State University; SUN, XIN - North Dakota State University

Submitted to: Smart Agricultural Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/14/2025
Publication Date: 6/14/2025
Citation: Mensah, B., Prasifka, J.R., Hulke, B.S., Monono, E., Sun, X. 2025. Detection of insect-damaged sunflower seeds using near-infrared hyperspectral imaging and machine learning. Smart Agricultural Technology. 12. https://doi.org/10.1016/j.atech.2025.101110.
DOI: https://doi.org/10.1016/j.atech.2025.101110

Interpretive Summary: Insect damage to seeds of sunflower or other crops reduces seed quality and crop profitability. Measuring amounts of seed damage is also important for work on insect management and plant breeding. This research tests whether images made with many different wavelengths of light (hyperspectral imaging) and computer analysis can be used to evaluate seed damage by one specific insect (the red sunflower seed weevil) accurately. Of several different methods, one was able to correctly score seeds as insect-damaged (or undamaged) more than 90% of the time. Though a trained person might score more than 90% of seeds correctly, the computer method is faster and can score seeds without getting tired. As a result, the approach using hyperspectral imaging provides an advantage when many groups of seeds need to be examined, as is common in commercial seed production or agricultural research.

Technical Abstract: Insect damage can significantly affect seed germination rates and overall quality, resulting in notable economic losses. Detecting insect-damaged seeds is vital for upholding food safety standards and satisfying consumer expectations. To tackle this issue, this study explores the potential of hyperspectral imaging combined with machine learning to accurately classify damaged and undamaged sunflower seeds. Spectral data were gathered and preprocessed using principal component analysis (PCA) to reduce dimensionality while retaining essential spectral information. Machine learning techniques, specifically multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), extreme gradient boosting (XGB), gradient boosting (GB), and partial least squares discriminant analysis (PLS-DA), were trained and evaluated based on the spectral features. The results showed that MLP achieved the highest classification performance with an accuracy of 0.91 and an F1-score of 0.91, followed by SVM with an accuracy of 0.89 and an F1-score of 0.89. LGBM and RF also performed well, both achieving an accuracy of 0.88 and an F1-score of 0.88, while XGB and GB recorded accuracies of 0.85 and 0.86, respectively. In contrast, PLS-DA demonstrated the lowest performance, with accuracy falling to 0.65 and an F1-score of 0.64. These findings underscore the effectiveness of machine learning in utilizing hyperspectral data for precise seed quality assessment. Its integration into the seed sorting process can enhance inspections, food safety, and ensure that only high-quality seeds are chosen for planting.