Visual assessment of raw materials in premix production using OpenCV
DOI:
https://doi.org/10.31548/energiya6(82).2025.107Abstract
The quality control of premix components is a crucial stage of their production. It directly influences a number of final product characteristics, including homogeneity, granulometric properties, and the effectiveness of the premix ingredients. This study highlights the relevance of using computer vision based on the OpenCV library for image processing of salt samples, as well as the application of deep learning with TensorFlow for automated quality classification. The results indicate whether the proposed tools are suitable for an efficient quality control process, enabling a reduction of human factor influence and improving the accuracy of defect detection.
Key words: computer vision, salt quality assessment, premix production, machine learning, OpenCV, TensorFlow
References
1. Victor Suresh, A. "Feed formulation software", Editor(s): Sergio F. Nates, Aquafeed Formulation, Academic Press, 2016, pp. 21-31, https://doi.org/10.1016/B978-0-12-800873-7.00002-6.
2. Heidari, M.D., Gandasasmita, S., Li, E., Pelletier, N. Proposing a framework for sustainable feed formulation for laying hens: A systematic review of recent developments and future directions, Journal of Cleaner Production, Vol. 288, 2021, https://doi.org/10.1016/j.jclepro.2020.125585 .
3. Wang, L.M., Mandell, I.B., Bohrer, B.M. "Effects of feeding essential oils and benzoic acid to replace antibiotics on finishing beef cattle growth, carcass characteristics, and sensory attributes, Applied" Animal Science, Vol.36 (2), 2020, pp. 145-156, https://doi.org/10.15232/aas.2019-01908
4. Khalid A. Abdoun, Gamaleldin M. Suliman, Ahmed A. Alsagan, Osman A. Altahir, Mohammed Y. Alsaiady, Elfadil E. Babiker, Mohammed A. Al-Badwi, Faisal A. Alshamiry, Ahmed A. Al-Haidary "Replacing alfalfa-based? total mixed ration with Moringa leaves for improving carcass and meat quality characteristics in lambs", Heliyon, Vol. 10 (17), 2024, e36863, https://doi.org/10.1016/j.heliyon.2024.e36863.
5. Kiktev, M. Formulation and solution of the problem of optimizing animal feeding [Postanovka ta vyrishennya zadachi optymizatsiyi hodivli tvaryn]. Technological audit and production reserves, 2013. - No. 6/2 (14). - pp.8-11. (In Ukranian).
6. Khort, D., Kutyrev, A., Smirnov, I., Osypenko, V., Kiktev, N. Computer vision system for recognizing the coordinates location and ripeness of strawberries. Communications in Computer and Information Science, vol. 1158, 2020, 3rd International Conference on Data Stream and Mining and Processing, DSMP 2020, Lviv.- pp. 334 – 343,
7. Bian, P., Li, W., Jin, Y. et al. Ensemble feature learning for material recognition with convolutional neural networks. J Image Video Proc. 2018, 64 (2018). https://doi.org/10.1186/s13640-018-0300-z
8. Xu, H., Han, Z., Feng, S. et al. Foreign object debris material recognition based on convolutional neural networks. J Image Video Proc. 2018, 21 (2018). https://doi.org/10.1186/s13640-018-0261-2
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Energy and Automation
All materials are disseminated under the terms of the Creative Commons Attribution 4.0 International Public License, which permits others to distribute the manuscript with proper acknowledgement of the authorship and the original publication in this journal.
