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 °Brix, 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 °Brix 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.

En este artículo se presenta información que busca establecer una base sobre la cual discutir el desarrollo de un software de enseñanza basado en simulación de ambientes virtuales, para su uso por parte de administradores y estudiantes del área técnica de manufactura en Chile. El objetivo general fue revisar la potencialidad y problemas de uso de software de simulación en nuestra sociedad digital. Se estudia críticamente el uso real de las Tecnologías de la Información y Comunicación (TIC) en la educación actual y se analiza la problemática en el uso pedagógico de los ambientes virtuales. Se concluye que el uso de las TIC debe tomar en consideración que las instituciones educativas han de desarrollar estrategias de apoyo al docente para que el uso de las TIC sea realmente un elemento positivo en el proceso formativo de los alumnos.

Raspberries are fruit of great importance for human beings. Their products are segmented by quality. However, estimating raspberry quality is a manual process carried out at the reception of the fruit processing plant, and is thus exposed to factors that could distort the measurement. The agriculture industry has increased the use of deep learning (DL) in computer vision systems. Non-destructive and computer vision equipment and methods are proposed to solve the problem of estimating the quality of raspberries in a tray. To solve the issue of estimating the quality of raspberries in a picking tray, prototype equipment is developed to determine the quality of raspberry trays using computer vision techniques and convolutional neural networks from images captured in the visible RGB spectrum. The Faster R–CNN object-detection algorithm is used, and different pretrained CNN networks are evaluated as a backbone to develop the software for the developed equipment. To avoid imbalance in the dataset, an individual object-detection model is trained and optimized for each detection class. Finally, both hardware and software are effectively integrated. A conceptual test is performed in a real industrial scenario, thus achieving an automatic evaluation of the quality of the raspberry tray, in this way eliminating the intervention of the human expert and eliminating errors involved in visual analysis. Excellent results were obtained in the conceptual test performed, reaching in some cases precision of 100%, reducing the evaluation time per raspberry tray image to 30 s on average, allowing the evaluation of a larger and representative sample of the raspberry batch arriving at the processing plant.

This work presents a free new database designed from a real industrial process to recognize, identify, and classify the quality of the red raspberry accurately, automatically, and in real time. Raspberry trays with recently harvested fresh fruit enter the industry’s selection and quality control process to be categorized and subsequently their purchase price is determined. This selection is carried out from a sample of a complete batch to evaluate the quality of the raspberry. This database aims to solve one of the major problems in the industry: evaluating the largest amount of fruit possible and not a single sample. This major dataset enables researchers in various disciplines to develop practical machine-learning (ML) algorithms to improve red raspberry quality in the industry, by identifying different diseases and defects in the fruit, and by overcoming limitations by increasing the performance detection rate accuracy and reducing computation time. This database is made up of two packages and can be downloaded free from the Laboratory of Technological Research in Pattern Recognition repository at the Catholic University of the Maule. The RGB image package contains 286 raw original images with a resolution of 3948 × 2748 pixels from raspberry trays acquired during a typical process in the industry. Furthermore, the labeled images are available with the annotations for two diseases (86 albinism labels and 164 fungus rust labels) and two defects (115 over-ripeness labels, and 244 peduncle labels). The MATLAB code package contains three well-known ML methodological approaches, which can be used to classify and detect the quality of red raspberries. Two are statistical-based learning methods for feature extraction coupled with a conventional artificial neural network (ANN) as a classifier and detector. The first method uses four predictive learning from descriptive statistical measures, such as variance, standard deviation, mean, and median. The second method uses three predictive learning from a statistical model based on the generalized extreme value distribution parameters, such as location, scale, and shape. The third ML approach uses a convolution neural network based on a pre-trained fastest region approach (Faster R-CNN) that extracts its features directly from images to classify and detect fruit quality. The classification performance metric was assessed in terms of true and false positive rates, and accuracy. On average, for all types of raspberries studied, the following accuracies were achieved: Faster R-CNN 91.2%, descriptive statistics 81%, and generalized extreme value 84.5%. These performance metrics were compared to manual data annotations by industry quality control staff, accomplishing the parameters and standards of agribusiness. This work shows promising results, which can shed a new light on fruit quality standards methodologies in the industry.

Lipid extraction using the traditional, destructive Soxhlet method is not able to measure oil content (OC) on a single olive. As the color and near infrared spectrum are key parameters to build an oil estimation model (EM), this study grouped olives with similar color and NIR for building EM of oil content obtained by Soxhlet from a cluster of similar olives. The objective was to estimate OC of individual olives, based on clusters of similar color and NIR in two seasons. This study was performed with Arbequina olives in 2016 and 2017. The descriptor of the cluster consisted of the three color channels of c1c2c3 color model plus 11 reflectance points between 1710 and 1735 nm of each olive, normalized with the Z-score index. Clusters of similar color and NIR spectrum were formed with the k-means++ algorithm, leaving a sufficient number of olives to perform the Soxhlet analysis of OC, as reference value of EM. The training of EM was based on Support Vector Machine. The test was performed with Leave One-Out Cross Validation in different training-testing combinations. The best EM predicted the OC with 6 and 13% deviation with respect to the real value when one season was tested with itself and with another season, respectively. The use of clustering in EM is discussed.