Using deep learning algorithms and a flatbed scanner to assess rice quality
Piotr Zapotoczny
WNT UWM w OlsztyniePrzemysław Karol Graczyk
Visacom Sp. z o.oAbstract
This article presents the results of research on the application of deep learning techniques in the automatic assessment of rice grain quality. A measurement methodology and a computer program were developed, which uses a deep learning model to identify individual grains in an image and detect impurities for further qualitative analysis. The program was implemented in Python using the OpenCV 4, Numpy, and Ultralytics YOLO libraries. The study used a flatbed scanner, enabling the identification of approximately 3,000 objects in a single scanner ruler pass.
Keywords:
deep learning, rice, segmentation, OpenCV, flatbed scannerSupporting Agencies
References
Aukkapinyo K., Sawangwong S., Pooyoi P., Kusakunniran W. 2020. Localization and classification of rice-grain images using region proposals-based convolutional neural network. International Journal of Automation and Computing, 17(2): 233-246. Google Scholar
Bienvenido O., Juliano A.P.P. 2019. Rice: Chemistry and Technology. Fourth Edition. American Association for Clinical Chemistry, Washington. Google Scholar
Borowy T., Kubiak M.S. 2014. Wartość technologiczna i żywieniowa ryżu. Przegląd Zbożowo-Młynarski, 58(3): 9-11. Google Scholar
Chollet F., 2019. Deep Learning: Praca z językiem Python i biblioteką Keras. Helion, Gliwice. Google Scholar
Dharmik R.C., Chavhan S., Gotarkar S., Pasoriya A. 2022. Rice quality analysis using image processing and machine learning. 3C TIC. Cuadernos de desarrollo aplicados a las TIC, 11(2): 158-164. Google Scholar
Elgendy M. 2020. Deep learning for vision systems. Manning Publications, Shelter Island. Google Scholar
Forsyth D.A., Ponce J. 2011. Computer vision: A modern approach. Prentice Hall, Saddle River. Google Scholar
Gao Q., Li H., Meng T., Xu X., Sun T., Yin L., Chai X. 2024. A rapid construction method for high-throughput wheat grain instance segmentation dataset using high-resolution images. Agronomy, 14(5): 1032. Google Scholar
Geron A. 2020. Uczenie maszynowe z użyciem Scikit-Learn i TensorFlow. Helion, Gliwice. Google Scholar
Gilanie G., Javed M., Rauf B., Cheema S., Latif A., Perveen S., Sajid M., Saeed M. 2021. RiceAgeNet: Age estimation of Pakistani grown rice seeds using convolutional neural networks. International Journal of Computational Intelligence in Control, 13(2): 831-843. Google Scholar
Gonzalez R.C., Woods R.E. 2001. Digital image processing. Second Edition. Prentice Hall, Saddle River. Google Scholar
Goodfellow I., Bengio Y., Courville A. 2016. Deep learning. The MIT Press, Cambridge. Google Scholar
He Y., Fan B., Sun L., Fan X., Zhang J., Li Y., Suo X. 2023. Rapid appearance quality of rice based on machine vision and convolutional neural network research on automatic detection system. Frontiers in Plant Science, 14: 1190591. Google Scholar
Howard J., Gugger S. 2020. Deep learning for coders with fastai and PyTorch. O’Reilly Media, Sebastopol. Google Scholar
Krizhevsky A., Sutskever I., Hinton G.E. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6): 84-90. Google Scholar
Li S., Li B., Li J., Liu B. 2022. Brown rice germ integrity identification based on deep learning network. Journal of Food Quality, 1. http://dx.doi.org/10.1155/2022/6709787 Google Scholar
Ma N., Li Z., Kong Q. 2024. Wheat grains automatic counting based on lightweight YOLOv8. INMATEH Agricultural Engineering, 73(2). Google Scholar
Matthes E. 2016. Python: Instrukcje dla programisty. Helion, Gliwice. Google Scholar
Mavaddati S., Razavi M. 2024. A CNN-LSTM-based approach for classification and quality detection of rice varieties. Journal of AI and Data Mining, 12(4): 473-485. Google Scholar
PN-ISO 7301:2004. Ryż – Wymagania. Polski Komitet Normalizacyjny, Warszawa. Google Scholar
Ramalho L. 2015. Zaawansowany Python. O’Reilly Media, Sebastopol. Google Scholar
Rath S. 2023. Getting started with YOLOv5 instance segmentation. LearnOpenCV. Retrieved from https://learnopencv.com/yolov5-instance-segmentation/ (29.08.2023). Google Scholar
Redmon J., Divvala S., Girshick R., Farhadi A. 2016. You only look once: unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788. Las Vegas. https://doi.org/10.1109/CVPR.2016.91 Google Scholar
Szelski R. 2022. Computer vision algorithms and applications. Second Edition. Springer Nature Switzerland, Cham. Google Scholar
Ultralytics YOLOv8. 2023. Ultralytics. Retrieved from github.com/ultralytics/ultralytics (29.08.2023). Google Scholar
Velesaca H.O., Suárez P.L., Mira R., Sappa A.D. 2021. Computer vision-based food grain classification: A comprehensive survey. Computers and Electronics in Agriculture, 187: 106287. Google Scholar
Wei J., Ni L., Luo L., Chen M., You M., Sun Y., Hu T. 2024. GFS-YOLO11: A maturity detection model for multi-variety tomato. Agronomy, 14: 2644. Google Scholar
Xu X., Geng Q., Gao F. 2023. Segmentation and counting of wheat spike grains based on deep learning and textural feature. Plant Methods, 19: 77. Google Scholar
Ziarno M., Zaręba D. 2008. Ryż - cenny składnik żywności. Przemysł Spożywczy, 62(5): 22-26. Google Scholar
WNT UWM w Olsztynie
Visacom Sp. z o.o
