Detecção de Patologias em Folhas de Tomateiros Utilizando Dois Classificadores

Early detection of pathologies in plantations using machine learning algorithms can drastically minimize the use of pesticides, reducing losses and improving food quality. In this scenario, this work proposes an approach based on the use of two convolutional neural networks (CNNs) acting in parallel to discriminate healthy leaves from leaves affected by pathologies. When compared to the classification performed by a single RNC, the approach proved to be efficient for small architectures, having the potential to improve data classification.