Key Points
- Researchers from the University of Belgrade demonstrated that combining Raman and FT-IR spectroscopy with machine learning algorithms, especially support vector machines (SVM), can accurately classify seed varieties of paprika, tomato, and lettuce, achieving up to 100% accuracy in some cases.
- Raman spectroscopy proved more sensitive than FT-IR in detecting molecular differences, and combining both methods further improved classification robustness while offering non-destructive, preparation-free, and rapid testing advantages.
- Despite promising results, challenges such as overfitting and model repeatability remain, highlighting the need for continued refinement to ensure broader applicability and long-term reliability in seed quality assessment and food fraud prevention.
A new study from the University of Belgrade has demonstrated the potential of combining Raman and Fourier-transform infrared (FT-IR) spectroscopy with advanced machine learning (ML) algorithms to accurately classify seed varieties in major vegetable crops. This study, which was published in the journal Plants, this research examined how this method can be used for crop variety discrimination and seed quality assurance (1).
What crops did the study investigate?
The researchers focused on three crops for their study: paprika (Capsicum annuum L.); tomato (Lycopersicon esculentum Mill.); and lettuce (Lactuca sativa L.). These crops were selected because these crops are highly sought after by consumers. Rather than comparing different crop species, which show macroscopic seed differences such as size and color, the research focuses on varietal differences within each species.
What was the experimental procedure?
As part of the experimental procedure, the researchers collected the spectral data from seed samples by using Raman spectroscopy and Fourier transform infrared (FT-IR) spectroscopy. Several pre-processing methods were used in the study, including smoothing, linear baseline correction, unit vector normalization, multiplicative scatter correction, and second-order derivatives (1). After pre-processing, principal component analysis (PCA) was employed to reduce dimensionality, followed by the application of various classification algorithms. The classification algorithms used were support vector machines (SVM), partial least squares discriminant analysis (PLS-DA), and PCA-quadratic discriminant analysis (PCA-QDA) (1).
Which model performed the best?
Out of all the models tested in the study, SVM consistently outperformed the others in classification accuracy. The researchers found that Raman spectroscopy paired with SVM achieved classification rates of 100.00% for lettuce, 99.37% for paprika, and 92.71% for tomato (1). FT-IR spectroscopy with SVM followed closely behind, with accuracy rates of 99.37% for lettuce, 92.50% for paprika, and 97.50% for tomato (1). When data from both Raman and FT-IR spectra were merged, classification accuracy improved even further, reaching 100.00% for lettuce and tomato, and 95.00% for paprika (1).
The results indicate that Raman spectroscopy is more sensitive than FT-IR in detecting molecular differences between seed varieties (1). Second, the results show that both techniques generally improve overall classification robustness when combined (1).
Using these methods offered several practical advantages. Both Raman and FT-IR spectroscopy are non-destructive, require no sample preparation, and deliver rapid results (2). These characteristics make Raman and FT-IR spectroscopy better alternative methods to traditional analysis.
Another important aspect to this study is that the results show that Raman imaging can help uncover chemical insights within seeds and other food products. As a result, Kolašinac and his team suggest that integrating two-dimensional (2D) and three-dimensional (3D) Raman imaging could visualize component distribution within seeds better (1).
What challenges still remain with the proposed method?
There are several key challenges the researchers found with this model. For example, overfitting is an issue that needs to be examined further, particularly when scaling up to broader genotype collections (1). For their model to be more widely used, future studies should examine improving model repeatability over time.
However, this study does show the importance of continuing to integrate ML with vibrational spectroscopy techniques like Raman. As the authors show in the study, doing so can improve seed quality and reduce food fraud, which will benefit consumers worldwide. These advancements can be expected to only get better as more researchers examine new ways to enhance quality detection of food.
References
- Kolašinac, S. M.; Mladenovic, M.; Pecinar, I.; et al. Raman and FT-IR Spectroscopy Coupled with Machine Learning for the Discrimination of Different Vegetable Crop Seed Varieties. Plants 2025, 14 (9), 1304. DOI: 10.3390/plants14091304.
- Horiba Scientific, What is Raman Spectroscopy? Horiba.com. Available at: https://www.horiba.com/int/scientific/technologies/raman-imaging-and-spectroscopy/raman-spectroscopy (accessed 2025-07-14).
