Classifying the Macronutrient Deficiency in Soybean Leaf with Deep Learning

  • Maicon Sartin Universidade do Estado de Mato Grosso
  • Alexandre da Silva Unesp
  • Claudinei Kappes Unesp
  • Tercio S. Filho UFG

Resumo


Deep Learning consiste em técnicas modernas que abordam um ou mais métodos de inteligência artificial. Uma abordagem está no uso de redes neurais convolucionais em conjunto com redes neurais tradicionais para processamento de imagens digitais. Neste trabalho, é realizada uma pesquisa para avaliar uma técnica de aprendizado profundo na classificação da deficiência de macronutrientes de potássio (K) pela folha de soja. Esta pesquisa apresenta um conjunto de dados próprio com tratamentos distintos do macronutriente de potássio. Vários cenários de aprendizado profundo são avaliados com diferentes métricas. Os resultados são comparados com a literatura e mostram um grande potencial de redes neurais convolucionais, com precisão acima de 99% nesse tipo de classificação.

Palavras-chave: Rede neural convolucional, classificação do macronutriente (K), aprendizado profundo, folha de soja.

Referências

Abdullahi, H. S., Sheriff, R., and Mahieddine, F. (2017). Convolution neural network in precision agriculture for plant image recognition and classification. In 2017 Seventh International Conference on Innovative Computing Technology (Intech), Ieee, Londrés, pages 1–3.

Boulent, J., Foucher, S., Théau, J., and St-Charles, P.-L. (2019). Convolutional neural networks for the automatic identification of plant diseases. Frontiers in plant science, 10. dos Santos Ferreira, A., Freitas, D. M., da Silva, G. G., Pistori, H., and Folhes, M. T. (2017). Weed detection in soybean crops using ConvNets. Computers and Electronics in Agriculture, 143:314–324.

Dosovitskiy, A., Springenberg, J. T., Riedmiller, M., and Brox, T. (2014). Discriminative unsupervised feature learning with convolutional neural networks. In Advances in neural information processing systems, pages 766–774.

Hasan, M. M., Chopin, J. P., Laga, H., and Miklavcic, S. J. (2018). Detection and analysis of wheat spikes using convolutional neural networks. Plant Methods, 14(1):100.

Kamilaris, A. and Prenafeta-Boldú, F. X. (2018). A review of the use of convolutional neural networks in agriculture. The Journal of Agricultural Science, 156(3):312–322.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105.

Lu, H., Fu, X., Liu, C., Li, L.-g., He, Y.-x., and Li, N.-w. (2017). Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning. Journal of Mountain Science, 14(4):731–741.

Lucchi, B. B., Conchon, R., Nakamura, C. Y., Alves, C. F., Schwantes, F., Rivaldo, G. C., Bianchi, I., Barros, L., and Camuri, P. A. (2020). Agropecuária cresce mais que a média da economia brasileira em 2019. techreport, Confederação da Agricultura e Pecuária do Brasil.

Rahnemoonfar, M. and Sheppard, C. (2017). Deep count: fruit counting based on deep simulated learning. Sensors, 17(4):905.

Sfredo, G. J. (2008). Soja no Brasil: calagem, adubação e nutrição mineral. Embrapa Soja Londrina.

Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. A. (2017). Inception-v4, inceptionresnet and the impact of residual connections on learning. In Thirty-first AAAI conference on artificial intelligence.

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9.

Taha, A. A. and Hanbury, A. (2015). Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC medical imaging, 15(1):29.

Tran, T.-T., Choi, J.-W., Le, T.-T. H., and Kim, J.-W. (2019). A comparative study of deep CNN in forecasting and classifying the macronutrient deficiencies on development of tomato plant. Applied Sciences, 9(8):1601.

Watchareeruetai, U., Noinongyao, P., Wattanapaiboonsuk, C., Khantiviriya, P., and Duangsrisai, S. (2018). Identification of plant nutrient deficiencies using convolutional neural networks. In 2018 International Electrical Engineering Congress (iEECON), pages 1–4. IEEE.

Wulandhari, L. A., Gunawan, A. A. S., Qurania, A., Harsani, P., Tarawan, T. F., and Hermawan, R. F. (2019). Plant nutrient deficiency detection using deep convolutional neural network. ICIC Express Letters, 13(10):971–977.

Xie, B., Zhang, H. K., and Xue, J. (2019). Deep convolutional neural network for mapping smallholder agriculture using high spatial resolution satellite image. Sensors, 19(10):2398.

Zhang, W., Li, R., Deng, H., Wang, L., Lin, W., Ji, S., and Shen, D. (2015). Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage, 108:214–224.
Publicado
20/10/2020
SARTIN, Maicon; DA SILVA, Alexandre; KAPPES, Claudinei; S. FILHO, Tercio. Classifying the Macronutrient Deficiency in Soybean Leaf with Deep Learning. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 17. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 638-649. ISSN 2763-9061. DOI: https://doi.org/10.5753/eniac.2020.12166.