Abstract
Light-based methods are being further developed to meet the growing demands for food in the agricultural industry. Optical imaging is a rapid, non-destructive, and accurate technology that can produce consistent measurements of product quality compared to conventional techniques. In this research, a novel approach for seed quality prediction is presented. In the proposed approach two advanced optical imaging techniques based on chlorophyll fluorescence and chemometric-based multispectral imaging were employed. The chemometrics encompassed principal component analysis (PCA) and quadratic discrimination analysis (QDA). Among plants that are relevant as both crops and scientific models, tomato, and carrot were selected for the experiment. We compared the optical imaging techniques to the traditional analytical methods used for quality characterization of commercial seedlots. Results showed that chlorophyll fluorescence-based technology is feasible to discriminate cultivars and to identify seedlots with lower physiological potential. The exploratory analysis of multispectral imaging data using a non-supervised approach (two-component PCA) allowed the characterization of differences between carrot cultivars, but not for tomato cultivars. A Random Forest (RF) classifier based on Gini importance was applied to multispectral data and it revealed the most meaningful bandwidths from 19 wavelengths for seed quality characterization. In order to validate the RF model, we selected the five most important wavelengths to be applied in a QDA-based model, and the model reached high accuracy to classify lots with high-and low-vigor seeds, with a correct classification from 86 to 95% in tomato and from 88 to 97% in carrot for validation set. Further analysis showed that low quality seeds resulted in seedlings with altered photosynthetic capacity and chlorophyll content. In conclusion, both chlorophyll fluorescence and chemometrics-based multispectral imaging can be applied as reliable proxies of the physiological potential in tomato and carrot seeds. From the practical point of view, such techniques/methodologies can be potentially used for screening low quality seeds in food and agricultural industries.
Highlights
Food quality and safety are the most important aspects in food and agricultural industries, which have been revolutionized by the development of more sophisticated, accurate and rapid testing methods that are mainly based on advanced optical imaging
In “Tyna” tomato, TIV and T-V lots were separated as lower performance in the early germination and accelerated aging tests, and these methods separated T-VI and T-VII with the best physiological potential
Chlorophyll fluorescence analysis at 620/730 nm excitationemission allows to separate tomato cultivars (Figure 4G), and at 645/700 nm discriminated cultivars in both tomato and carrot (Figures 4C,D)
Summary
Food quality and safety are the most important aspects in food and agricultural industries, which have been revolutionized by the development of more sophisticated, accurate and rapid testing methods that are mainly based on advanced optical imaging. Chlorophyll fluorescence-based technology is centered on the capacity of chlorophyll, which is often present in seeds during their development to emit light in a slightly longer wavelength in relation to the light that was absorbed (Misra et al, 2012; Smolikova et al, 2017). Multispectral imaging is a non-destructive technology able to integrate the conventional vision and spectroscopy technique to obtain at same time spatial and spectral information of an object (Shrestha et al, 2015; Mastrangelo et al, 2019; França-Silva et al, 2020), with accurate measurements of uniform and nonhomogeneous samples. The basic principle of this technique is that all types of materials reflect and absorb electromagnetic energy in different patterns at specific wavelengths because of the difference in their physical structure and chemical composition. There are still some challenges regarding data interpretation and analysis; in such situations, mathematical chemometric models can underpin the dominant patterns in large data matrices in a fast and robust manner (ElMasry et al, 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
