What is it about?
This research explores an innovative way to detect hidden pest damage in fresh asparagus without cutting or damaging the product. The study combines hyperspectral imaging, a technology that captures information beyond what the human eye can see, with artificial intelligence to identify asparagus affected by Elasmopalpus lignosellus. By analyzing how asparagus reflects light at different wavelengths, machine learning models can distinguish healthy spears from infested ones. The results demonstrate the potential of this technology as a reliable, non-destructive solution for improving asparagus quality inspection and supporting smarter food production systems.
Featured Image
Why is it important?
Detecting internal pest damage in asparagus is a major challenge for the food industry because affected products may appear healthy on the outside. Traditional visual inspection can miss these hidden defects, potentially leading to economic losses, product rejection, and reduced consumer confidence. Our research demonstrates that combining hyperspectral imaging with machine learning can achieve 97.9% classification accuracy in external validation. This approach offers a promising alternative for non-destructive quality control, helping producers and exporters improve inspection accuracy, reduce unnecessary product waste, and move toward more efficient, automated, and sustainable food quality assurance systems.
Perspectives
This research highlights the growing potential of artificial intelligence and advanced optical technologies to transform agricultural and food quality inspection. In the future, hyperspectral imaging could be integrated into automated sorting and inspection systems to identify internal defects in fresh produce more efficiently. Further research should evaluate the technology under real industrial conditions, including different asparagus varieties, production environments, and processing speeds. Beyond asparagus, this approach could also inspire new applications for detecting hidden damage in other agricultural products, contributing to smarter, more sustainable, and data-driven food supply chains.
PhD Jimy Oblitas
Universidad Privada del Norte
Read the Original
This page is a summary of: Non-Destructive Detection of Elasmopalpus lignosellus Infestation in Fresh Asparagus Using VIS–NIR Hyperspectral Imaging and Machine Learning, Foods, January 2026, MDPI AG,
DOI: 10.3390/foods15020355.
You can read the full text:
Contributors
The following have contributed to this page
