Ripeness estimation of grape berries and seeds by image analysis

• Published in: Computers and electronics in agriculture Vol. 82; pp. 128 - 133
• Main Authors: Rodríguez-Pulido, Francisco J, Gómez-Robledo, Luis, Melgosa, Manuel, Gordillo, Belén, González-Miret, M. Lourdes, Heredia, Francisco J
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.03.2012; Elsevier
• Subjects: Agronomy. Soil science and plant productions; Biological and medical sciences; chemical analysis; chemical composition; color; Colour; computer vision; discriminant analysis; Fundamental and applied biological sciences. Psychology; Grape seeds; grapes; Image analysis; quality control; red wines; Ripeness; seeds; Vitis vinifera; Image analysis; Ripeness; Grape seeds; Vitis vinifera; Colour; Berry; Color; Fruit crop; Vitidaceae; Dicotyledones; Grape; Angiospermae; Spermatophyta; Maturity
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2012.01.004

Digital imaging has become a powerful tool for the characterization and quality control of foodstuff. Because of the need to automate processes, faster tools are needed and Computer Vision is a good alternative to chemical analysis of many products in quality control. Appearance of grape seeds and grape berries change during the ripeness. These changes are closely related to the chemical composition, especially phenolics, which are very important compounds due to their implications on the intensity and stability of red wine colour. In this study, a complete characterization of grape seeds and grape berries by digital image analysis is described. The size of grapes and the veraison has been determined by image analysis and it has been also established an objective Browning Index of seeds. Morphological differences between varieties were studied by applying discriminant analysis models which allowed us to classify the grape seeds with high accuracy.