AMIPDI: architecture model to identify pests in soybean defoliation images using convolutional neural networks

Authors

  • Maria Eloisa Mignoni UNEMAT
  • Aislan Honorato Centro Universitário de Várzea Grande - UNIVAG
  • Cesar Zagonel University of Cruzeiro do Sul - UNICSUL
  • Gabriel de Oliveira Ramos Unisinos
  • Rafael Kunst Kunst University of Vale do Rio dos Sinos - Unisinos

DOI:

https://doi.org/10.5335/rbca.v17i2.16186

Keywords:

Soybean, Deep Learning, Pest, Defoliates, Agriculture

Abstract

Pests that attack crops are one of the leading causes of low production and economic losses. Identifying and diagnosing
forecasts is one way to reduce losses and maintain quality in production. Defoliation of crops harms production and
production quality. Using computational technologies such as Artificial Intelligence andMachine Learning has enabled
the identification of pests faster and earlier. In this paper, we propose a Deep Learning-based architecture aimed at
identifying and diagnosing insects by analyzing defoliation in crop images. Different Convolutional Neural Network
approacheswere considered to evaluate the proposed architecture. The training and testing of themodelswere performed
using images collected by drone in a natural environment. The approach that presented the best performance in our
scenario was the VGG16. The average accuracy in the validation phase was 0.95, while in the test set, we obtained 0.86.

Downloads

Download data is not yet available.

Downloads

Published

2025-08-16

Issue

Section

Original Paper

How to Cite

[1]
2025. AMIPDI: architecture model to identify pests in soybean defoliation images using convolutional neural networks. Brazilian Journal of Applied Computing. 17, 2 (Aug. 2025), 11–20. DOI:https://doi.org/10.5335/rbca.v17i2.16186.