![[2602.12313] Visible and Hyperspectral Imaging for Quality Assessment of Milk: Property Characterisation and Identification](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.12313] Visible and Hyperspectral Imaging for Quality Assessment of Milk: Property Characterisation and Identification
Summary
This study explores the use of visible and hyperspectral imaging for the rapid, non-destructive assessment of milk quality, demonstrating high accuracy in characterizing biochemical properties using machine learning techniques.
Why It Matters
With increasing concerns over food safety and nutritional quality, this research highlights innovative imaging techniques as cost-effective alternatives to traditional chemical analyses, potentially transforming quality assessment in the dairy industry.
Key Takeaways
- Visible and hyperspectral imaging can accurately assess milk quality.
- Machine learning algorithms achieved 100% accuracy in distinguishing fresh from stored milk.
- The study demonstrates the potential for non-invasive quality control in the dairy sector.
Electrical Engineering and Systems Science > Image and Video Processing arXiv:2602.12313 (eess) [Submitted on 12 Feb 2026] Title:Visible and Hyperspectral Imaging for Quality Assessment of Milk: Property Characterisation and Identification Authors:Massimo Martinelli, Elena Tomassi, Nafiou Arouna, Morena Gabriele, Laryssa Perez Fabbri, Luisa Pozzo, Giuseppe Conte, Davide Moroni, Laura Pucci View a PDF of the paper titled Visible and Hyperspectral Imaging for Quality Assessment of Milk: Property Characterisation and Identification, by Massimo Martinelli and 8 other authors View PDF Abstract:Rapid and non-destructive assessment of milk quality is crucial to ensuring both nutritional value and food safety. In this study, we investigated the potential of visible and hyperspectral imaging as cost-effective and quick-response alternatives to conventional chemical analyses for characterizing key properties of cowś milk. A total of 52 milk samples were analysed to determine their biochemical composition (polyphenols, antioxidant capacity, and fatty acids) using spectrophotometer methods and standard gas-liquid and high-performance liquid chromatography (GLC/HPLC). Concurrently, visible (RGB) images were captured using a standard smartphone, and hyperspectral data were acquired in the near-infrared range. A comprehensive analytical framework, including eleven different machine learning algorithms, was employed to correlate imaging features with biochemical measurements. Analysis of ...