This review highlights how modern spectroscopy and hyperspectral imaging address yogurt adulteration, suggesting machine learning may further enhance detection accuracy.
Yogurt is a valued dairy product known for its taste and texture, but these qualities also make it prone to adulteration. Common practices include adding starch, milk powders, vegetable oils, sweeteners, preservatives, and, in some cases, even harmful heavy metals, which can reduce quality and harm consumer health. Conventional analysis can be selective but is often destructive, labor-intensive, and slow for routine screening. The rapid, non-destructive alternatives provided by modern image-based spectroscopy can probe both composition and spatial heterogeneity in yogurt. This review summarizes the developments of hyperspectral imaging (HSI) and new spectroscopic methods of detecting yogurt adulterants, including Near-Infrared (NIR), Terahertz spectroscopy, Raman, Laser-Induced Breakdown Spectroscopy (LIBS), Nuclear Magnetic Resonance (NMR), vibrational mid-IR/FTIR, and UV-V are prominent methods. Spectroscopy gives robust chemical fingerprints (NIR/Raman/FTIR), and HSI gives space (LIBS/THz), as well as elemental and bulk properties; the combination of the two with ML enhances the precision and generalization. Key challenges include product variability, fermentation effects, calibration transfer, and the lack of publicly available datasets. To address these, future priorities should focus on developing portable instruments, applying multimodal data fusion and transfer learning, ensuring interpretable AI models, and establishing standardized protocols for routine, non-destructive yogurt authenticity testing.
No takes yet. Share an insight, caveat, or question.
Aqeel et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: