Proposed Approach for Creating Soybean Grain Image Dataset
Resumo
The integration of digital technologies and artificial intelligence in agriculture has the potential to significantly improve the accuracy and efficiency of grain classification. This study focuses on the development of a comprehensive methodology for soybean grain classification, utilizing a custom-built image acquisition system and advanced image processing techniques. High-resolution images of soybean grains were captured using a Nikon D3100 DSLR camera, with the setup optimized to ensure consistent lighting and contrast for precise image analysis. Various segmentation methods, including RGB and CMYK color channel separation, Otsu thresholding, and edge detection using the Canny algorithm, were employed to isolate and classify key features of the grains. Classical image processing techniques were used to create a robust and labeled dataset, providing essential training data for machine learning models. The results demonstrate the potential of combining classical image segmentation with machine learning to automate grain classification processes, enhancing reliability and ensuring compliance with industry standards.
Referências
F. J. Rodríguez-Pulido, D. F. Barbin, D. W. Sun, B. Gordillo, M. L. González-Miret, and F. J. Heredia, “Grape seed characterization by NIR hyperspectral imaging,” Postharvest Biology and Technology, vol. 76, pp. 74–82, 2013. [Online]. Available: DOI: 10.1016/j.postharvbio.2012.09.007
K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine Learning in Agriculture: A Review.” [Online]. Available: [link]
W. Lin, Y. Fu, P. Xu, S. Liu, D. Ma, Z. Jiang, S. Zang, H. Yao, and Q. Su, “Soybean image dataset for classification,” Data in Brief, vol. 48, jun 2023.
Nikon, “History of nikon products: 2010s,” [link], 2010, acessado em: Setembro 12, 2024.
G. Laing, “Nikon d3100 review,” 2024, accessed: 2024-09-20. [Online]. Available: [link]
W. Lin, Y. Lin, J. Phys, J. Chen, Z. Gao, and C. Huang, “Soybean image segmentation based on multi-scale Retinex with color restoration You may also like Underwater image enhancement algorithm based on Retinex and wavelet fusion Soybean image segmentation based on multi-scale Retinex with color restoration,” Journal of Physics: Conference Series, vol. 2284, p. 12010, 2022.
R. Andrade and C. A. Schneider, A cor: teoria e prática, Universidade Federal do Paraná, 2014, material da aula 2 do curso de Desenho Industrial. [Online]. Available: [link]
U. F. do Ceará, “Padrão de cor rgb e cmyk,” 2024, accessed: 2024-09-20. [Online]. Available: [link]
K. Kiratiratanapruk and W. Sinthupinyo, “Color and texture for corn seed classification by machine vision,” 2011 International Symposium on Intelligent Signal Processing and Communications Systems: ”The Decade of Intelligent and Green Signal Processing and Communications”, ISPACS 2011, pp. 7–11, 2011.
Y. Li, J. Jia, L. Zhang, A. M. Khattak, S. Sun, W. Gao, and M. Wang, “Soybean seed counting based on pod image using two-column convolution neural network,” IEEE Access, vol. 7, pp. 64 177–64 185, 2019.
Y. T. Tovar, A. F. Calvo, and A. Bejarano, “Desarrollo de un sistema de clasificación de imágenes digitales para medir la humedad en granos de café” Información tecnológica, vol. 33, no. 3, pp. 117–128, 2022.
G. Research, “Google colaboratory faq,” 2024, accessed: 2024-09-20. [Online]. Available: [link]
N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp.62–66, 1979.
O. Team, “Opencv documentation,” 2024, accessed: 2024-09-21. [Online]. Available: [link]
H. Vu, V. N. Duong, and T. T. Nguyen, “Inspecting rice seed species purity on a large dataset using geometrical and morphological features,” ACM International Conference Proceeding Series, pp. 321–328, 2018.
J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679–698, 1986.
T. Matos Maruyama, M. Hosoya Name, J. Rissa Franco, and R. Falate, “Development and Validation of a Method for Measurement of Root Length in 2D Images,” IEEE Latin America Transactions, vol. 16, no. 3, pp. 940–947, mar 2018.
