Periódicos

URI permanente desta comunidadehttps://thoth.dti.ufv.br/handle/123456789/3352

Navegar

Filtros

2020 - 20212

Configurações

Assunto: search.filters.subject.Classification

Resultados da Pesquisa

Agora exibindo 1 - 2 de 2
  • Imagem de Miniatura
    Item
    Determination of physical and chemical quality of coffee beans under improved potassium fertilization managements
    (Editora UFLA, 2021) Moreira, Diulie Talita; Mellis, Estêvão Vicari; Giomo, Gerson Silva; Teixeira, Luiz Antonio Junqueira; Cavalli, Edilson; Ramos, Lucas Ferreira
    Coffee quality is the key attribute for establishing its price and commercialization. As the classification of coffee quality is a complex process, mainly based on a subjective judgment, difficult to define and measure, a complementary approach to the current procedures involving physical and chemical methods would bring more effectiveness to the process of quality determination. The chemical composition of the coffee bean is influenced by several factors, among them the nutritional management of coffee trees and, the use of potassium chloride (KCl), which has intensified losses in bean quality due to excessive chlorine in its composition. The aim of this study was to evaluate the efficiency of sources and forms of K application in the quality of beans, and assessment of methodologies for determination of physical and chemical qualities of beans. The experiment was conducted with Yellow Ca tuaí cultivar, from 2017 to 2019, in a randomized experimental block design with five replicates. Six treatments were applied, containing proportions of KCl/K2SO4, as follows: T1-100% KCl; T2-75%/25%; T3-50%/50%; T4-25%/75%; T5-100% of K2SO4 and T6-100% of KCl + two foliar K2SO4 applications. The variables addressed in the study were sensory analysis, screen of beans, electrical conductivity (EC), potassium leaching (KL), titratable total acidity (TTA), and coffee bean color. It was verified that KL, EC, and other chromatic parameters were efficient in detecting alterations on coffee bean caused by the use of KC1. Total (T5) or partial (T4) replacement of KC1 by K2SO4 applied to soil improved chemical characteristics and color of coffee beans. Supplemental foliar fertilization with K2SO4 (T6) was efficient to minimize deleterious effects of KCl on quality of coffee beans, improving beverage quality and grain size, especially in high productive harvests.
  • Imagem de Miniatura
    Item
    Quality assessment of coffee beans through computer vision and machine learning algorithms
    (Editora UFLA, 2020) Santos, Fernando Ferreira Lima dos; Rosas, Jorge Tadeu Fim; Martins, Rodrigo Nogueira; Araújo, Guilherme de Moura; Viana, Lucas de Arruda; Gonçalves, Juliano de Paula
    The increasing market interest in coffee beverage, lead coffee growers around the world to adopt more efficient methods to select the best-quality coffee beans. Currently, coffee beans selection is carried out either manually, which is a costly and unreliable process, or using electronic sorting machines, which are often inefficient because some coffee beans defects, such as sour and immature beans, have similar spectral response patterns. In this sense, the present work aimed to analyze the importance of shape and color features for different machine learning techniques, such as Support Vector Machine (SVM), Deep Neural Network (DNN) and Random Forest (RF), to assess coffee beans’ defects. For this purpose, an algorithm written in Python language was used to extract shape and color features from coffee beans images. The dataset obtained was then used as input to the machine learning algorithms, developed using Python and R programing languages. The data reported in this study pointed to the importance of color descriptors for classifying coffee beans defects. Among the variables used, the components Gmean from RGB (Red, Green and Blue) color space and Vmean from HSV (Hue, Saturation and Value) color space were some of the most relevant features for the classification models. The results reported in this study indicate that all the classifier models presented similar performance. In addition, computer vision along with machine learning algorithms can be used to classify coffee beans with a very high accuracy (> 88%).