Estudo comparativo entre Máquina de Vetores de Suporte e Rede Neural Convolucional na classificação do inseto Diaphorina citri
Resumo
O inseto Diaphorina citri é o principal propagador da doença dos citros Huanglongbing. Para o controle do problema, os insetos são capturados por armadilhas adesivas e contados manualmente, para ajuste da dosagem de inseticida. Assim, este trabalho teve como objetivo medir e analisar o desempenho da classificação automática do Diaphorina citri a partir de abordagens de Aprendizado de Máquina. Para o treinamento dos modelos foi criado um banco de imagens e utilizadas as abordagens de Máquina de Vetores de Suporte (SVM) e Rede Neural Convolucional (CNN). A CNN, com o modelo Inception v3, apresentou em média 99.37% de acurácia na classificação final do Diaphorina citri, resultado significativo em relação aos 97.99% apresentado pela SVM.
Palavras-chave:
Rede Neural Convolucional, Máquina de Vetores de Suporte, Diaphorina citri, Huanglongbing, Greening
Referências
Bay, H., Ess, A., Tuytelaars, T., e Van Gool, L. (2008). Speeded-up robust features (surf). Computer vision and image understanding, 110(3):346–359. DOI: https://doi.org/10.1016/j.cviu.2007.09.014
Belasque Junior, J., Bergamin Filho, A., Bassanezi, R. B., Barbosa, J. C., Fernandes, N. G., Yamamoto, P. T., Lopes, S. A., Machado, M. A., Leite Junior, R. P., Ayres, A. J., et al. (2009). Base cientı́fica para a erradicação de plantas sintomáticas e assintomáticas de huanglongbing (hlb, greening) visando o controle efetivo da doença. Tropical Plant Pathology, 34(3):137–145. DOI: https://doi.org/10.1590/S1982-56762009000300001
Boiman, O., Shechtman, E., e Irani, M. (2008). In defense of nearest-neighbor based image classification. In 2008 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8. IEEE. DOI: 10.1109/CVPR.2008.4587598
Bosch, A., Munoz, X., e Marti, R. (2007). Which is the best way to organize/classify images by content? Image and vision computing, 25(6):778–791. DOI: http://dx.doi.org/10.1016/j.imavis.2006.07.015
Chaplot, S., Patnaik, L. M., e Jagannathan, N. (2006). Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomedical signal processing and control, 1(1):86–92. DOI: https://doi.org/10.1016/j.bspc.2006.05.002
Gallo, D., Nakano, O., Silveira Neto, S., Carvalho, R. P. L., e Baptista, G. C. d. (2002). Entomologia agrı́cola. Fundação de Estudos Agrários Luiz de Queiroz, 632.7 edition.
Hackeling, G. (2017). Mastering Machine Learning with scikit-learn. Packt Publishing Ltd.
Halbert, S. E. e Manjunath, K. L. (2004). Asian citrus psyllids (sternorrhyncha: Psyllidae) and greening disease of citrus: a literature review and assessment of risk in florida. Florida entomologist, 87(3):330–353. DOI: https://doi.org/10.1653/0015-4040(2004)087[0330:ACPSPA]2.0.CO;2
Japkowicz, N. e Shah, M. (2011). Evaluating learning algorithms: a classification perspective. Cambridge University Press.
Japkowicz, N. e Stephen, S. (2002). The class imbalance problem: A systematic study. Intelligent data analysis, 6(5):429–449. DOI: http://dx.doi.org/10.3233/IDA-2002-6504
Kingma, D. P. e Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Kotsia, I. e Pitas, I. (2006). Facial expression recognition in image sequences using geometric deformation features and support vector machines. IEEE transactions on image processing, 16(1):172–187. DOI: https://doi.org/10.1109/TIP.2006.884954
Krizhevsky, A., Sutskever, I., e Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25:1097–1105. DOI: https://doi.org/10.5555/2999134.2999257
Leonardo, A. (2014). Otimização da leitura de cartão adesivo amarelo para o monitoramento de adultos de diaphorina citri kuwayama (hemiptera: Liviidae). Master’s thesis, Fundo de Defesa da Citricultura.
Liu, Z., Gao, J., Yang, G., Zhang, H., e He, Y. (2016). Localization and classification of paddy field pests using a saliency map and deep convolutional neural network. Scientific reports, 6(1):1–12. DOI: https://doi.org/10.1038/srep20410
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110. DOI: https://doi.org/10.1023/B:VISI.0000029664.99615.94
Nava, D., Torres, M., Rodrigues, M., Bento, J., e Parra, J. (2007). Biology of diaphorina citri (hem., psyllidae) on different hosts and at different temperatures. Journal of Applied Entomology, 131(9-10):709–715. DOI: https://doi.org/10.1111/j.1439-0418.2007.01230.x
Neves, M. F., Trombin, V., Milan, P., Lopes, F., Cressoni, F., e Kalaki, R. (2010). O retrato da citricultura brasileira. Ribeirão Preto: CitrusBR, page 137.
Shen, Y., Zhou, H., Li, J., Jian, F., e Jayas, D. S. (2018). Detection of stored-grain insects using deep learning. Computers and Electronics in Agriculture, 145:319–325. DOI: http://dx.doi.org/10.1016/j.compag.2017.11.039
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., e Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826. DOI: https://doi.org/10.1109/CVPR.2016.308
Tieleman, T., Hinton, G., et al. (2012). Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2):26–31.
Tsai, C.-F. (2012). Bag-of-words representation in image annotation: A review. International Scholarly Research Notices, 2012. DOI: https://doi.org/10.5402/2012/376804
Venugoban, K. e Ramanan, A. (2014). Image classification of paddy field insect pests using gradient-based features. International Journal of Machine Learning and Computing, 4(1):1. DOI: http://dx.doi.org/10.7763/IJMLC.2014.V4.376
Yamamoto, P. T., Fellipe, M. R., Sanches, A. L., Coelho, J. H., Garbim, L. F., e Ximenes, N. L. (2009). Eficácia de inseticidas para o manejo de diaphorina citri kuwayama (hemiptera: Psyllidae) em citros. BioAssay, 4. DOI: http://dx.doi.org/10.14295/BA.v4.0.21
Belasque Junior, J., Bergamin Filho, A., Bassanezi, R. B., Barbosa, J. C., Fernandes, N. G., Yamamoto, P. T., Lopes, S. A., Machado, M. A., Leite Junior, R. P., Ayres, A. J., et al. (2009). Base cientı́fica para a erradicação de plantas sintomáticas e assintomáticas de huanglongbing (hlb, greening) visando o controle efetivo da doença. Tropical Plant Pathology, 34(3):137–145. DOI: https://doi.org/10.1590/S1982-56762009000300001
Boiman, O., Shechtman, E., e Irani, M. (2008). In defense of nearest-neighbor based image classification. In 2008 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8. IEEE. DOI: 10.1109/CVPR.2008.4587598
Bosch, A., Munoz, X., e Marti, R. (2007). Which is the best way to organize/classify images by content? Image and vision computing, 25(6):778–791. DOI: http://dx.doi.org/10.1016/j.imavis.2006.07.015
Chaplot, S., Patnaik, L. M., e Jagannathan, N. (2006). Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomedical signal processing and control, 1(1):86–92. DOI: https://doi.org/10.1016/j.bspc.2006.05.002
Gallo, D., Nakano, O., Silveira Neto, S., Carvalho, R. P. L., e Baptista, G. C. d. (2002). Entomologia agrı́cola. Fundação de Estudos Agrários Luiz de Queiroz, 632.7 edition.
Hackeling, G. (2017). Mastering Machine Learning with scikit-learn. Packt Publishing Ltd.
Halbert, S. E. e Manjunath, K. L. (2004). Asian citrus psyllids (sternorrhyncha: Psyllidae) and greening disease of citrus: a literature review and assessment of risk in florida. Florida entomologist, 87(3):330–353. DOI: https://doi.org/10.1653/0015-4040(2004)087[0330:ACPSPA]2.0.CO;2
Japkowicz, N. e Shah, M. (2011). Evaluating learning algorithms: a classification perspective. Cambridge University Press.
Japkowicz, N. e Stephen, S. (2002). The class imbalance problem: A systematic study. Intelligent data analysis, 6(5):429–449. DOI: http://dx.doi.org/10.3233/IDA-2002-6504
Kingma, D. P. e Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Kotsia, I. e Pitas, I. (2006). Facial expression recognition in image sequences using geometric deformation features and support vector machines. IEEE transactions on image processing, 16(1):172–187. DOI: https://doi.org/10.1109/TIP.2006.884954
Krizhevsky, A., Sutskever, I., e Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25:1097–1105. DOI: https://doi.org/10.5555/2999134.2999257
Leonardo, A. (2014). Otimização da leitura de cartão adesivo amarelo para o monitoramento de adultos de diaphorina citri kuwayama (hemiptera: Liviidae). Master’s thesis, Fundo de Defesa da Citricultura.
Liu, Z., Gao, J., Yang, G., Zhang, H., e He, Y. (2016). Localization and classification of paddy field pests using a saliency map and deep convolutional neural network. Scientific reports, 6(1):1–12. DOI: https://doi.org/10.1038/srep20410
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110. DOI: https://doi.org/10.1023/B:VISI.0000029664.99615.94
Nava, D., Torres, M., Rodrigues, M., Bento, J., e Parra, J. (2007). Biology of diaphorina citri (hem., psyllidae) on different hosts and at different temperatures. Journal of Applied Entomology, 131(9-10):709–715. DOI: https://doi.org/10.1111/j.1439-0418.2007.01230.x
Neves, M. F., Trombin, V., Milan, P., Lopes, F., Cressoni, F., e Kalaki, R. (2010). O retrato da citricultura brasileira. Ribeirão Preto: CitrusBR, page 137.
Shen, Y., Zhou, H., Li, J., Jian, F., e Jayas, D. S. (2018). Detection of stored-grain insects using deep learning. Computers and Electronics in Agriculture, 145:319–325. DOI: http://dx.doi.org/10.1016/j.compag.2017.11.039
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., e Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826. DOI: https://doi.org/10.1109/CVPR.2016.308
Tieleman, T., Hinton, G., et al. (2012). Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2):26–31.
Tsai, C.-F. (2012). Bag-of-words representation in image annotation: A review. International Scholarly Research Notices, 2012. DOI: https://doi.org/10.5402/2012/376804
Venugoban, K. e Ramanan, A. (2014). Image classification of paddy field insect pests using gradient-based features. International Journal of Machine Learning and Computing, 4(1):1. DOI: http://dx.doi.org/10.7763/IJMLC.2014.V4.376
Yamamoto, P. T., Fellipe, M. R., Sanches, A. L., Coelho, J. H., Garbim, L. F., e Ximenes, N. L. (2009). Eficácia de inseticidas para o manejo de diaphorina citri kuwayama (hemiptera: Psyllidae) em citros. BioAssay, 4. DOI: http://dx.doi.org/10.14295/BA.v4.0.21
Publicado
10/11/2021
Como Citar
PIERRE JÚNIOR, Mário Lúcio G. de Q.; MELO, José Leonardo dos S.; MIRANDA, Marcelo P. de; ANGELO, Michele Fúlvia.
Estudo comparativo entre Máquina de Vetores de Suporte e Rede Neural Convolucional na classificação do inseto Diaphorina citri. In: CONGRESSO BRASILEIRO DE AGROINFORMÁTICA (SBIAGRO), 13. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 126-135.
ISSN 2177-9724.
DOI: https://doi.org/10.5753/sbiagro.2021.18383.
