A Deep Learning Approach for Soybean Grain Quality Analysis Using Multispectral Images
Resumo
Este trabalho propõe uma abordagem para classificação de grãos de soja usando imagens multiespectrais obtidas por equipamento de baixo custo desenvolvido pela OpenScience. A metodologia combina segmentação com Cellpose, redes neurais convolucionais em TensorFlow e PCA para redução de dimensionalidade. Com 10 componentes principais, o modelo obteve acurácia de 95%, indicando alto desempenho preditivo. Este estudo contribui para a aplicação de tecnologias acessíveis no setor agrícola, abrindo caminho para futuras pesquisas sobre a adaptação do modelo ao contexto industrial.Referências
Bianchini, V. d. J. M., Mascarin, G. M., Silva, L. C. A. S., Arthur, V., Carstensen, J. M., Boelt, B., and Barboza da Silva, C. (2021). Multispectral and x-ray images for characterization of jatropha curcas l. seed quality. Plant Methods, 17:1–13.
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., and Belongie, S. (2019). Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9268–9277.
Delwiche, S. and Miskelly, D. (2017). Chapter 19 - analysis of grain quality at receival. In Wrigley, C., Batey, I., and Miskelly, D., editors, Cereal Grains (Second Edition), Woodhead Publishing Series in Food Science, Technology and Nutrition, pages 513–570. Woodhead Publishing, second edition edition.
Dieleman, S. (2020). Deep Learning Lecture 3: Convolutional Neural Networks. [link]. Acesso em: 23 out. 2024.
Fernandes, F. A. N., Rodrigues, S., and Alves Filho, E. G. (2024). Chemometrics: Data Treatment and Applications. Elsevier.
Jing, S., Li, X., Shi, J., Zhuo, Z., Sun, W., Ni, J., and Tan, K. (2026). Vigor detection of soybean seeds using hyperspectral imaging and machine learning. Agriculture, 16(11):1174.
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90.
Kurita, T. (2021). Principal component analysis (pca). In Computer vision: a reference guide, pages 1013–1016. Springer.
Li, F.-F., Johnson, J., and Yeung, S. (2018). Convolutional neural networks. Disponível em: [link].
Marques, V. G., Ribas, L. C., and Ranieri, C. M. (2025). Comparative analysis of deep learning architectures for classifying soy seeds. In Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), pages 748–759. SBC.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Sabin, G. P. (2024). Sistema, processo e método para classificação de café. Pedido de patente BR 10 2023 008919-4 A2. Depositante: Guilherme Post Sabin Consultoria Científica e Inteligência Analítica LTDA ME. Publicado na RPI 2811, em 19 nov. 2024. Depósito em 10 maio 2023.
Scherer, D., Müller, A., and Behnke, S. (2010). Evaluation of pooling operations in convolutional architectures for object recognition. In International conference on artificial neural networks, pages 92–101. Springer.
Shea, E., Perera, F., and Mills, D. (2020). Towards a fuller assessment of the economic benefits of reducing air pollution from fossil fuel combustion: Per-case monetary estimates for children’s health outcomes. Environmental Research, 182:109019.
Shinde-Patil, S. S., Desai, V. P., and Prathapan Pillai, K. (2024). Deep learning-based analysis, selection, and detection of soybean seeds: A comprehensive review. In International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, pages 115–127. Springer.
Shorten, C. and Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1):1–48.
Stringer, C., Wang, T., Michaelos, M., and Pachitariu, M. (2021). Cellpose: a generalist algorithm for cellular segmentation. Nature methods, 18(1):100–106.
Tian, S. and Xu, H. (2022). Nondestructive methods for the quality assessment of fruits and vegetables considering their physical and biological variability. Food Engineering Reviews, 14(3):380–407.
Tripathy, B. K., Sundareswaran, A., and Ghela, S. (2021). Unsupervised learning approaches for dimensionality reduction and data visualization. CRC Press.
Xie, W., Wang, F., and Yang, D. (2019). Research on carrot surface defect detection methods based on machine vision. IFAC-PapersOnLine, 52(30):24–29.
Zhang, A., Lipton, Z. C., Li, M., and Smola, A. J. (2021). Dive into deep learning. arXiv preprint arXiv:2106.11342.
Zhao, G., Quan, L., Li, H., Feng, H., Li, S., Zhang, S., and Liu, R. (2021). Real-time recognition system of soybean seed full-surface defects based on deep learning. Computers and Electronics in Agriculture, 187:106230.
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., and Belongie, S. (2019). Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9268–9277.
Delwiche, S. and Miskelly, D. (2017). Chapter 19 - analysis of grain quality at receival. In Wrigley, C., Batey, I., and Miskelly, D., editors, Cereal Grains (Second Edition), Woodhead Publishing Series in Food Science, Technology and Nutrition, pages 513–570. Woodhead Publishing, second edition edition.
Dieleman, S. (2020). Deep Learning Lecture 3: Convolutional Neural Networks. [link]. Acesso em: 23 out. 2024.
Fernandes, F. A. N., Rodrigues, S., and Alves Filho, E. G. (2024). Chemometrics: Data Treatment and Applications. Elsevier.
Jing, S., Li, X., Shi, J., Zhuo, Z., Sun, W., Ni, J., and Tan, K. (2026). Vigor detection of soybean seeds using hyperspectral imaging and machine learning. Agriculture, 16(11):1174.
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90.
Kurita, T. (2021). Principal component analysis (pca). In Computer vision: a reference guide, pages 1013–1016. Springer.
Li, F.-F., Johnson, J., and Yeung, S. (2018). Convolutional neural networks. Disponível em: [link].
Marques, V. G., Ribas, L. C., and Ranieri, C. M. (2025). Comparative analysis of deep learning architectures for classifying soy seeds. In Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), pages 748–759. SBC.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Sabin, G. P. (2024). Sistema, processo e método para classificação de café. Pedido de patente BR 10 2023 008919-4 A2. Depositante: Guilherme Post Sabin Consultoria Científica e Inteligência Analítica LTDA ME. Publicado na RPI 2811, em 19 nov. 2024. Depósito em 10 maio 2023.
Scherer, D., Müller, A., and Behnke, S. (2010). Evaluation of pooling operations in convolutional architectures for object recognition. In International conference on artificial neural networks, pages 92–101. Springer.
Shea, E., Perera, F., and Mills, D. (2020). Towards a fuller assessment of the economic benefits of reducing air pollution from fossil fuel combustion: Per-case monetary estimates for children’s health outcomes. Environmental Research, 182:109019.
Shinde-Patil, S. S., Desai, V. P., and Prathapan Pillai, K. (2024). Deep learning-based analysis, selection, and detection of soybean seeds: A comprehensive review. In International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, pages 115–127. Springer.
Shorten, C. and Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1):1–48.
Stringer, C., Wang, T., Michaelos, M., and Pachitariu, M. (2021). Cellpose: a generalist algorithm for cellular segmentation. Nature methods, 18(1):100–106.
Tian, S. and Xu, H. (2022). Nondestructive methods for the quality assessment of fruits and vegetables considering their physical and biological variability. Food Engineering Reviews, 14(3):380–407.
Tripathy, B. K., Sundareswaran, A., and Ghela, S. (2021). Unsupervised learning approaches for dimensionality reduction and data visualization. CRC Press.
Xie, W., Wang, F., and Yang, D. (2019). Research on carrot surface defect detection methods based on machine vision. IFAC-PapersOnLine, 52(30):24–29.
Zhang, A., Lipton, Z. C., Li, M., and Smola, A. J. (2021). Dive into deep learning. arXiv preprint arXiv:2106.11342.
Zhao, G., Quan, L., Li, H., Feng, H., Li, S., Zhang, S., and Liu, R. (2021). Real-time recognition system of soybean seed full-surface defects based on deep learning. Computers and Electronics in Agriculture, 187:106230.
Publicado
19/10/2026
Como Citar
SILVA, Eduardo Oliveira; SABIN, Gustavo Post; TAKAGI, Nilton Hideki; MARINS, Joyce Aline de Oliveira.
A Deep Learning Approach for Soybean Grain Quality Analysis Using Multispectral Images. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 457-468.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.30020.
