Classification of Weeds in Agricultural Crops with Ensembles of Convolutional Neural Networks

• Vitor Carvalho Universidade do Estado do Amazonas
• Elloá Guedes Universidade do Estado do Amazonas
• Marcos Salame Embrapa Amazônia Ocidental

DOI: https://doi.org/10.5753/eniac.2019.9272

Abstract

The present work aimed at proposing and evaluation ensembles of convolutional neural networks to address the classification of agricultural crops versus weeds from images of seedlings in their early stages. To do so, there was a training data preparation phase, adoption of five convolutional neural network architectures and the proposition of three ensemble with different vo- ting strategies. Upon considering the performance of individual networks, an accuracy of 95.77% was reported for MobileNet, meanwhile the ensemble with Support Vector Machine smart voting had accuracy of 97.08%. The results ob- tained consider a Computational Vision task that enhances the development of digital agriculture, favoring a better yield of agricultural production.

Keywords: Applications of Artificial Intelligence, Deep Learning, Computer Vision

References

Alimboyong, C. R., Hernandez, A. A., and Medina, R. P. (2018). Classication of plant seedling images using deep learning. In IEEE TENCON Region 10 Conference, pages 1839–1844, Coréia do Sul. IEEE.

Alimboyong, C. R., Hernandez, A. A., and Medina, R. P. (2019). An improved deep neural network for classication of plant seedling images. In IEEE 15th International Colloquium on Signal Processing & its Applications, pages 217–222, Malásia. IEEE.

Chollet, F. (2018). Deep Learming with Python. Manning Publications, Nova Iorque, Estados Unidos, 1 edition.

Christoffoleti, P. J. and Passini, T. (1999). Manejo integrado de plantas daninhas na cultura do feijão. FANCELLI, A. L.; DOURADO NETO, D. Feijão irrigado: estratégias básicas de manejo.

da Silva, A. A., Silva, J. F., Ferreira, F. A., Ferreira, L. R., and Silva, R. R. (1999). Controle de plantas daninhas. Abeas, Brasília, DF, 1 edition.

de Oliveira Jr., R. S., Constantin, J., and Inoue, M. H. (2011). Biologia e manejo de plantas daninhas. Omnipax, Brasil, 1 edition.

Dyrmann, M., Christiansen, P., and Midtiby, H. S. (2018). Estimation of plant species by classifying plants and leaves in combination. J Field Robotics., 35:202–212.

Embrapa (2014). Visão 2014–2034 – o futuro do desenvolvimento tecnológico da agricultura brasileira (síntese).

Freeman, I., Roese-Koerner, L., and Kummert, A. (2018). Effnet: An efcient structure for convolutional neural networks. http://arxiv.org/abs/1801.06434.

Giselsson, T. M., Jørgensen, R. N., Jensen, P. K., Dyrmann, M., and Midtiby, H. S. (2017). A public image database for benchmark of plant seedling classication algorithms.

Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efcient convolutional neural networks for mobile vision applications. http://arxiv.org/abs/1704.04861.

Kamilaris, A. and Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147:70–90.

Khan, S., Rahmani, H., Shah, S. A. A., and Bennamoun, M. (2018). A Guide to Convolutional Neural Networks for Computer Vision. Morgan & Claypool, Austrália, 1 edition.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classication with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, pages 1097–1105, Estados Unidos. Association for Computing Machinery.

LeCun, Y., , Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324.

MAPA (2019). Ministério da agricultura, pecuária e abastecimento, panorama do agronegócio brasileiro. Disponível em http://www.agricultura.gov.br. Acesso em 26 de jun. de 2019.

Melhorança, A. L. and Karam, D. (2019). Tratos culturais. Disponível em http://bit.ly/2xaSIk7. Acesso em 25 de jun. de 2019.

IEEE Circuits and Polikar, R. (2006). Ensemble based systems in decision making. Systems Magazine, 6(3):21–45.

Polikar, R. (2012). Ensemble Learning, pages 1–34. Springer Science+Business Media, Estados Unidos. Capítulo do livro: “Ensemble Machine Learning: Methods and Applications”, (C. Zhang & Y. Ma, eds.).

Rokach, L. (2010). Ensemble-based classiers. Artif Intell Rev, 33:1–39.

Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. pages 1–14, Estados Unidos.

Tang, S., Zhu, Q., Zhou, X., Liu, S., and Wu, M. (2002). A conception of digital agriIn IEEE International Geoscience and Remote Sensing Symposium, pages culture. 3026–3028, Canada. IEEE.

Vibhute, A. and Bodhe, S. K. (2012). Applications of image processing in agriculture: A survey. International Journal of Computer Applications, 52(2):34–40.

Voll, E., Adegas, F. S., Gazziero, D. L. P., Brighenti, A. M., and de Oliveira, M. C. N. (2003). Amostragem do banco de sementes da ora emergente de plantas daninhas. Pesquisa Agropecuária Brasileira, 38(2):211–218.

Zhang, C. and Ma, Y. (2012). Ensemble Machine Learning: Methods and Applications. Springer Science+Business Media, Estados Unidos.

Zhang, X., Zhou, X., Lin, M., and Sun, J. (2017). Shufenet: An extremely efcient convolutional neural network for mobile devices. http://arxiv.org/abs/1707. 01083.