Visão Computacional na Agricultura de Precisão: Uma Análise Comparativa de Arquiteturas CNN no Diagnóstico de Doenças Foliares do Milho
Resumo
O milho é um pilar do agronegócio brasileiro, mas sua produção é ameaçada por doenças foliares que demandam diagnóstico rápido e preciso. Como solução, este artigo apresenta uma análise comparativa de quatro arquiteturas de Visão Computacional (InceptionV3, ResNet50, ResNet152 e DenseNet201) aplicadas à classificação dessas doenças, com foco na realidade da região do MATOPIBA. O objetivo é avaliar a performance e a eficiência de cada modelo para subsidiar o desenvolvimento de uma ferramenta de detecção precoce eficaz, capaz de reduzir custos, promover a sustentabilidade e aumentar a rentabilidade para os produtores, em linha com o Plano de Soberania Digital do Brasil.Referências
Ghose, S. and Others (2020). Corn or Maize Leaf Disease Dataset. Acesso em: ago. 2025.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.
Jasrotia, S., Yadav, J., Rajpal, N., Arora, M., and Chaudhary, J. (2023). Convolutional neural network based maize plant disease identification. Procedia Computer Science, 218:1712–1721.
Kumar, A., Nelson, L., and Venu, V. S. (2024). Efficientnet-b1 based maize plant leaf disease classification using deep learning. In 2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), pages 1636–1642. IEEE.
Ma, Z., Wang, Y., Zhang, T., Wang, H., Jia, Y., Gao, R., and Su, Z. (2022). Maize leaf disease identification using deep transfer convolutional neural networks. International Journal of Agricultural and Biological Engineering, 15:187–195.
Mumuni, A. and Mumuni, F. (2022). Data augmentation: A comprehensive survey of modern approaches. Array, 16:100258.
Singh, G., Guleria, K., and Sharma, S. (2024). Leveraging transfer learning-based fine-tuned resnet50 model for maize leaf disease classification. In 2024 5th International Conference for Emerging Technology (INCET), pages 1–6. IEEE.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.
Jasrotia, S., Yadav, J., Rajpal, N., Arora, M., and Chaudhary, J. (2023). Convolutional neural network based maize plant disease identification. Procedia Computer Science, 218:1712–1721.
Kumar, A., Nelson, L., and Venu, V. S. (2024). Efficientnet-b1 based maize plant leaf disease classification using deep learning. In 2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), pages 1636–1642. IEEE.
Ma, Z., Wang, Y., Zhang, T., Wang, H., Jia, Y., Gao, R., and Su, Z. (2022). Maize leaf disease identification using deep transfer convolutional neural networks. International Journal of Agricultural and Biological Engineering, 15:187–195.
Mumuni, A. and Mumuni, F. (2022). Data augmentation: A comprehensive survey of modern approaches. Array, 16:100258.
Singh, G., Guleria, K., and Sharma, S. (2024). Leveraging transfer learning-based fine-tuned resnet50 model for maize leaf disease classification. In 2024 5th International Conference for Emerging Technology (INCET), pages 1–6. IEEE.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
Publicado
12/11/2025
Como Citar
RIBEIRO, Jhonatas Gomes; REIS, Igor Bezerra.
Visão Computacional na Agricultura de Precisão: Uma Análise Comparativa de Arquiteturas CNN no Diagnóstico de Doenças Foliares do Milho. In: ESCOLA REGIONAL DE APRENDIZADO DE MÁQUINA E INTELIGÊNCIA ARTIFICIAL DA REGIÃO SUL (ERAMIA-RS), 1. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 364-367.
DOI: https://doi.org/10.5753/eramiars.2025.16735.
