Evaluation of deep learning approaches in the identification and classification of fungal spores from microscopy slides
Resumo
Soybean cultivation is one of the principal crops in agricultural production in Brazil, moving a relevant agribusiness production chain. However, there are problems during the production process, involving care from planting, development to harvesting. In particular, the control of pests such as fungi is of great relevance to production. Monitoring and decision-making for the prevention and application of fungicides in the sector has become a major focus in terms of sustainability, productivity, and healthier production for human and animal consumption. Computational approaches have been applied to pest monitoring, however they focus on detecting the phenotype of diseases, when cultivars already show signs of infection and require fungicide application. However, fungi reproduces through living hosts and uses the wind to migrate its spores to a new host, such as Asian soybean rust. One possibility for early identification, before the manifestation of the pathology, is to detect the presence of spores by spore collectors and microscopy slides. But this leads to manual analysis performed by a specialist, being a time-consuming and tiring process. Deep Learning approaches can assign greater accuracy when counting spores with less time, finding patterns and leading to classification. Therefore, this study presents an evaluation of different deep learning approaches for the automatic recognition of spores that cause soybean diseases: rust, downy mildew, and powdery mildew from microscopy slides.
Referências
Bevers, N., Sikora, E. J., and Hardy, N. B. (2022). Soybean disease identification using original field images and transfer learning with convolutional neural networks. Computers and Electronics in Agriculture, 203:107449.
Brilhador, A., Colonhezi, T. P., Bugatti, P. H., and Lopes, F. M. (2013). Combining texture and shape descriptors for bioimages classification: a case of study in imageclef dataset. In LNCS, pages 431–438. Springer.
de Oliveira, G. M., Heling, A. L., Possamai, E. J., Seixas, C. D. S., Conte, O., Igarashi, W. T., and Igarashi, S. (2020). Coletor de esporos: descrição, uso e resultados no manejo da ferrugem-asiática da soja. CIRCULAR TÉCNICA 167.
Godoy, C. V., Almeida, A., Costamilan, L., Meyer, M., Dias, W. P., Seixas, C., Soares, R., Henning, A., Yorinori, J., Ferreira, L., et al. (2016). Doenças da soja. Manual de fitopatologia, 2:657–675.
Godoy, C. V. and Canteri, M. G. (2004). Efeito da severidade de oídio e crestamento foliar de cercospora na produtividade da cultura da soja. Fitopatologia brasileira, 29:526-530.
Gong, H., Mu, T., Li, Q., Dai, H., Li, C., He, Z., Wang, W., Han, F., Tuniyazi, A., Li, H., et al. (2022). Swin-transformer-enabled yolov5 with attention mechanism for small object detection on satellite images. Remote Sensing, 14(12):2861.
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.
Hirakuri, M. H. (2020). O contexto econômico da produção de soja. In Seixas, C. D. S., Neumaier, N., Junior, A. A. B., Krzyzanowski, F. C., and de Campos Leite, R. M. V. B., editors, Tecnologias de produção de soja. Embrapa.
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.
IBGE, A. (2023). Ibge prevê safra de 308,5 milhões de toneladas para 2024, com queda de 2,8% frente a 2023.
Igarashi, S., Oliveira, G., Camargo, L., Falkoski Filho, J., Gardiano, C., and Balan, M. (2020). Danos causados pela infecção de oídio em diferentes estádios fenológicos da soja. Arquivos do Instituto Biológico, 77:245–250.
Im Choi, J. and Tian, Q. (2022). Adversarial attack and defense of yolo detectors in autonomous driving scenarios. In 2022 IEEE Intelligent Vehicles Symposium (IV), pages 1011–1017. IEEE.
Lei, Y., Yao, Z., and He, D. (2018). Automatic detection and counting of urediniospores of puccinia striiformis f. sp. tritici using spore traps and image processing. Scientific reports, 8(1):13647.
Oliveira, G. d., Seixas, C., Reis, E., Heling, A., Silva, G., Possamai, E., Lima, D. d., and de Oliveira, A. (2023). Monitoramento de phakopsora pachyrhizi na safra 2021/2022 para tomada de decisão do controle da ferrugem-asiática da soja. In 38 Reunião de Pesquisa de Soja, pages 91–94. Embrapa.
Pereira, D. F., Bugatti, P. H., Lopes, F. M., de Souza, A. L. S. M., and Saito, P. T. M. (2020). Assessing active learning strategies to improve the quality control of the soy-bean seed vigor. IEEE Transactions on Industrial Electronics, 68(2):1675–1683.
Shahoveisi, F., Taheri Gorji, H., Shahabi, S., Hosseinirad, S., Markell, S., and Vasefi, F. (2023). Application of image processing and transfer learning for the detection of rust disease. Scientific Reports, 13(1):5133.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, K., Kumar, S., and Kaur, P. (2019). Support vector machine classifier based detection of fungal rust disease in pea plant (pisam sativam). International Journal of Information Technology, 11:485–492.
Sohan, M., Sai Ram, T., Reddy, R., and Venkata, C. (2024). A review on yolov8 and its advancements. In International Conference on Data Intelligence and Cognitive Informatics, pages 529–545. Springer.
