No abstract

Background The San Francisco Valley region from Brazil is known worldwide for its fruit production and exportation, especially grapes and wines. The grapes have high quality not only due to the excellent morphological characteristics, but also to the pleasant taste of their fruits. Such features are obtained because of the climatic conditions present in the region. In addition to the favorable climate for grape cultivation, harvesting at the right time interferes with fruit properties. Results This work aims to define grape maturation stage of Syrah and Cabernet Sauvignon cultivars with the aid of deep‐learning models. The idea of working with these algorithms came from the fact that the techniques commonly used to find the ideal harvesting point are invasive, expensive, and take a long time to get their results. In this work, convolutional neural networks were used in an image classification system, in which grape images were acquired, preprocessed, and classified based on their maturation stage. Images were acquired with varying illuminants that were considered as parameters of the classification models, as well as the different post‐harvesting weeks. The best models achieved maturation classification accuracy of 93.41% and 72.66% for Syrah and Cabernet Sauvignon respectively. Conclusions It was possible to correctly classify wine grapes using computational intelligent algorithms with high accuracy, regarding the harvesting time, corroborating chemometric results. © 2020 Society of Chemical Industry

The present work provides a methodology for automated image processing and classification of four types of insulators used in Overhead Power Distribution Lines (OPDLs). To this end, a didactic distribution network was developed to capture photos of the insulators at an external environment as well as a studio to acquire images at a controlled environment. Subsequently, the image attributes where extracted and used as inputs for diferent trained classifiers such as neural networks, suport vector machine, decision tree, n-nearest neigbors, naive-bayes and hidden markov model, for a gradual mixing ofthe databases (studio and external imagens). The classification efficiencies where compared considering the application of principal components analysis (PCA) to identify the minimum information required for the classification.

No abstract