Evaluation and Optimization of an AI Model for European Canker Detection

• Camile Coelho Arruda IFSC
• Jonatam Sturcio Corrêa IFSC
• Wilson Castello Branco Neto IFSC
• Robson Costa IFSC

DOI: https://doi.org/10.5753/eramiars.2025.16618

Resumo

European canker, caused by Neonectria ditissima, is one of the most destructive diseases affecting apple orchards worldwide. Early and accurate diagnosis is essential to reduce economic losses, but traditional methods rely on expert visual inspection, which is often slow and subjective. Advances in Convolutional Neural Networks (CNNs) have shown great potential for plant disease detection by enabling automated image-based diagnosis. This work investigates the application of pre-trained CNN architectures to the identification of European canker symptoms in apple branches. The study demonstrates that CNNs can achieve promising results, although challenges remain due to the complexity of branch-based symptoms compared to leaf diseases.

Referências

Ahmed, S. et al. (2025). Cucunetcnns: Application of novel ensemble deep neural networks for classification of cucumber leaf disease. Ain Shams Eng. Journal, 16.

Al-Gaashani, M. S. A. M., Shang, F., e El-Latif, A. A. A. (2022). Ensemble learning of lightweight deep convolutional neural networks for crop disease image detection. World Scientific Journals, 32(5).

Branco Neto, W. C., Araujo, L., Pinto, F. A. M. F., Machado, R. A., Ribeiro, Y. F. B., Cordova Junior, W. F., e Mattos, K. M. (2021). Cancontrol: plataforma para diagnóstico do cancro europeu da macieira. In Anais do XIII Congresso Brasileiro de Agroinformática, pages 44–52, Porto Alegre, RS, Brasil. SBC.

Harteveld, D. O. C., Goedhart, P., Houwers, I., Kohl, J., de Jong, P., e Wenneker, M. (2023). Detecting the asymptomatic colonization of apple branches by neonectria ditissima, causing european canker of apple. SpringerNature Complete Journals, 166(3):291–301.

Khan, S. et al. (2024). Smart agriculture: An intelligent approach for apple leaf disease identification based on convolutional neural network. International Journal of Intelligent Systems, 172(4).

Kumar, P., Gupta, G., et al. (2023). A systematic analysis of machine learning and deep learning based approaches for identifying and diagnosing plant diseases. Sustainable Operations and Computers.

Min, B., Kim, T., Shin, D., e Shin, D. (2023). Data augmentation method for plant leaf disease recognition. Applied Sciences, 13(3):1465.

Mohanty, S. P., Hughes, D. P., e Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7:1419.

Rana, A. et al. (2022). A comprehensive review on detection of plant disease using machine learning and deep learning approaches. Computers and Electronics in Agriculture, 24.

Zhang, L. et al. (2021). Disease detection in apple leaves using deep convolutional neural network. Agriculture, 11(7):617.