Convolutional Neural Networks for Leaf Disease Classification

• Raí G. Carvalho IESB
• Leticia T. M. Zoby IESB

DOI: https://doi.org/10.5753/eniac.2018.4428

Resumo

This paper aims to improve the classification process of leaf diseases in plantations, reducing the need to have a specialist or prior knowledge of the diseases that can affect a plantation, since some diseases can spread and end with entire plantations. The proposal is the use of Convolutional Neural Networks (CNN) to classify leaf diseases in plants using images, creating a model that can be implemented in a smartphone application. The model selected for the application, using a dataset with 4485 images separated in 5 classes, had an accuracy of 97% in the test base.

Referências

Alammar, J. (2016), https://jalammar.github.io/visual-interactive-guide-basics-neural-networks/

Cerda, R., Avelino, J., Gary, C., et al. (2017) “Primary and Secondary Yield Losses Caused by Pests and Diseases: Assessment and Modeling in Coffee”, In: GAIA.

Costa, C. C., Guilhoto, J. J. M. and Burnquist, H. L. (2015) “Impactos Socioeconômicos de Reduções nas Perdas Pós-colheita de Produtos Agrícolas no Brasil”, In: RESR, v. 53, p. 395-408.

Ferreira, S. (2017) “Redes Neurais Convolucionais Profundas na Detecção de Plantas Daninhas em Lavoura de Soja”, In: UFMG.

Garrido, L. R. and Gava, R. (2014) “Manual de doenças fúngicas da videira”, In: Embrapa.

Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., and Wang, G. (2015). “Recent advances in convolutional neural networks”, In: arXiv preprint arXiv:1512.07108.

IBGE (2006) “Censo Agropecuário”, In: Instituto Brasileiro de Geografia e Estatística, https://biblioteca.ibge.gov.br/visualizacao/periodicos/50/agro_2006_agricultura_familiar.pdf

ILSVRC (2012) “ImageNet Large Scale Visual Recognition Challenge”, In: ImageNet, http://image-net.org/challenges/LSVRC/2012/index

Jassmann, T. J., Tashakkori, R., and Parry, R. M. (2015) “Leaf classification utilizing a convolutional neural network”, In SoutheastCon 2015, pages 1–3. IEEE.

Kingma, D. P. and Ba, J. L. (2015) “Adam: A Method for Stochastic Optimization”, In: ICLR.

Kreyci, P. F. and Menten, J. O. (2013) “Limitadoras de produtividade”, In: Cultivar Caderno Técnico, v. 167, p. 1-12.

Krizhevsky, A., Sutskever, I. and Geoffrey, E. H. (2012) “ImageNet Classification with Deep Convolutional Neural Networks”, In: NIPS, p. 1-9.

Petrellis, N. (2015) “Plant Disease Diagnosis Based on Image Processing, Appropriate for Mobile Phone Implementation”, In: HAICTA, p. 238-246.

PlantVillage (2017), https://plantvillage.psu.edu/

Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D. and Stefanovic, D. (2016) “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification”, In: Computational Intelligence and Neuroscience, v. 2016, p. 11. Sousa, A. L., Salame, M. F. A., Nascimento Filho, F. J. and Atroch, A. L. (2017) “Redes Neurais Convolucionais Aplicadas ao Processo de Classificação de Cultivares de Guaranazeiros”, In: XIV Encontro Nacional de Inteligência Artificial e Computacional

Tensorflow (2017), https://www.tensorflow.org/

USDA (2017) “World Agricultural Production”, In: Circular Series, http://apps.fas.usda.gov/psdonline/circulars/production.pdf

Zuza, J. L. M. F. and Borsato, J. M. S. L. (2013) “Análise de oerdas agrícolas e econômicas ocasionada pela doença ferrugem alaranjada em canaviais comerciais de uma empresa de bioenergia no interior de São Paulo”, In: XX Congresso Brasileiro de Custos, p. 13.