Computer vision system and hyperspectral imaging for non-destructive and contactless estimation of maturity index and vitamin C in Candonga strawberry
Rattachement africain : it. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
The rapid, non-destructive and contactless assessment of fruit maturity and nutritional quality is a key challenge for precision harvesting and postharvest management. This study evaluated the potential of a hyperspectral spectroradiometer, and a Computer Vision System (CVS) based on calibrated color images to predict maturity index and vitamin C content in Candonga strawberries harvested at two ripening stages (nearly mature, 50-70% red surface colouration, and mature, 100% red surface colouration) from three farms. Fruits were subjected to non-destructive and contactless measurements and subsequently analyzed through destructive laboratory assays. Mature fruits showed a high respiration rate and maturity index, whereas nearly mature strawberries exhibited high titratable acidity and vitamin C content. Hyperspectral data were preprocessed and modeled using multiple regression approaches. Linear regression achieved the best performance for maturity index prediction and vitamin C content (R² = 0.81 ± 0.03 and R² = 0.69 ± 0.05, respectively). The analysis of the importance of features consistently identified key spectral regions associated with color changes and antioxidant compounds. Furthermore, the CVS, based on calibrated color images and Forest regression, demonstrated suitable predictive capability, with determination coefficients up to R 2 = 0.71 for maturity index and R 2 = 0.63 for vitamin C. The performance of CVS was lower than hyperspectral analysis due to the cumulative spectral nature of color channels, but color analysis is simpler, faster and cheaper and represent an interesting alternative in specific tasks along the supply chain. The experiments proved both hyperspectral and CVS to be effective for the non-destructive estimation of internal quality attributes in strawberries. The results obtained support the use of optical sensing technologies for real-time quality monitoring and improved decision-making along the strawberry supply chain.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Computer vision system and hyperspectral imaging for non-destructive and contactless estimation of maturity index and vitamin C in Candonga strawberry
- Date Crossref
- 01/08/2026
- Éditeur
- Elsevier BV
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Institute of Sciences of Food Production pays non établi dans la noticeStructure de recherche
-
Institute of Atmospheric Sciences and Climate pays non établi dans la noticeStructure de recherche
-
National Research Council pays non établi dans la noticeOrganisation à but non lucratif
-
Institute of Intelligent Industrial Systems and Technologies for Advanced Manufacturing pays non établi dans la noticeStructure de recherche
-
Institute of Bio Economy pays non établi dans la noticeStructure de recherche
-
Institute of Polar Sciences pays non établi dans la noticeStructure de recherche
-
Institute on Intelligent Industrial Systems and Technologies for Advanced Manufacturing pays non établi dans la noticeStructure de recherche
Institute of Sciences of Food Production, Institute of Atmospheric Sciences and Climate et National Research Council, avec 4 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.