Agriculture has always been an important economic and social sector for humans. Fruit production is especially essential, with a great demand from all households. Therefore, the use of innovative technologies is of vital importance for the agri-food sector. Currently artificial intelligence is one very important technological tool widely used in modern society. Particularly, Deep Learning (DL) has several applications due to its ability to learn robust representations from images. Convolutional Neural Networks (CNN) is the main DL architecture for image classification. Based on the great attention that CNNs have had in the last years, we present a review of the use of CNN applied to different automatic processing tasks of fruit images: classification, quality control, and detection. We observe that in the last two years (2019–2020), the use of CNN for fruit recognition has greatly increased obtaining excellent results, either by using new models or with pre-trained networks for transfer learning. It is worth noting that different types of images are used in datasets according to the task performed. Besides, this article presents the fundamentals, tools, and two examples of the use of CNNs for fruit sorting and quality control.
Sensory evaluation of grapes (Vitis vinifera L.) plays a key role in determining the harvest time in grapevine varieties. The harvest time of cv. Carménère is one of the latest of Chile. During the season 2007-2008, the evolution of the appearance of Carménère seeds was evaluated as a harvest criterion, comparing it with the chemical and phenolic ripening. The samples were obtained from an organic vineyard located in Curicó Valley, Chile. Starting at 16 ºBrix, 100 seed berries samples were collected weekly from medium vigor vines in order to register photographically the ventral and dorsal sides of each seed. In addition to the seed tannins percentage, the extractable anthocyanins, total anthocyanins and total polyphenols index, as well as the titratable acidity, soluble solids and pH were registered. A color wheel of seed coat with a description of 12 digital colors was proposed for this cultivar. When the color number exceeded 10 (very dark brown), the soluble solids had already reached 24 ºBrix 1 month earlier. Two inverse correlations between seed coat color vs. seed phenols percentage and vs. total polyphenol index were found. The proper phenolic maturation (maximum anthocyanins and minimum seed tannins percentage) occurred 177 d post flowering. The observation of seed coat color can be a reliable, simple and low-cost parameter to determine the correct ripeness of phenols in 'Carménère' grapevines.
Vitis vinifera cv. Carménère is a vigorous variety of grapevine that requires high temperatures and luminosity for achieving optimal phenolic maturity and herbal aromas, which has been reported to significantly delay harvest in Chile. This research was developed under the hypothesis that canopy management, vigor and crop load could modify the productive and vegetative relationships for obtaining early or late ripening and achieving vine balance. The aim of this study was to determine the vine balance and the time of ripeness for Carménère grapevines. Different vigor and canopy managements were evaluated. The study was conducted in the Central Valley of Chile during the 2007 to 2008 season with own-rooted Carménère vines trained to a four-cane vertical shoot position (VSP) located on high growth potential soil. The ripeness was delayed with high vigor and high crop load. In this growing condition, an early ripeness was reached with spur pruning, low vigor and by cluster thinning. In addition, the appropriate vine balance was only obtained in vines with low vigor and 50% cluster thinning. Together, these data demonstrate the vine balance of Carménère under these management conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.