Abstract

The article examines the application of machine vision technologies to enhance the accuracy and efficiency of grain material identification during post-harvest processing. It has been determined that traditional grain quality control methods, including visual, microbiological, and chemical tests, have significant limitations in identifying impurities, especially those similar in physical and visual characteristics. In response to these challenges, a digital grain identification algorithm based on machine vision and machine learning methods is proposed. The algorithm allows for rapid and accurate analysis of grain material images, enabling automatic recognition, classification, and quality assessment. Additionally, the algorithm shows potential for scalability and integration into modern agro-industrial processes, helping to minimize grain loss and improve preservation during transportation and storage. This positions machine vision technologies as a promising tool for ensuring food security in Ukraine. The article summarizes global experience in digital object identification in images and highlights possible methods for identifying grain materials, facilitating the development of the algorithm. A preliminary version of the digital identification algorithm for grain materials has been developed, incorporating relevant methods that enable recognition, classification, and evaluation of grain material indicators. Convolutional Neural Networks (CNNs) have been found to be the main type of neural networks for working with images, which are specialized for processing data with mesh topology. They have become very popular in computer vision tasks, including object recognition, image segmentation, and classification, due to their ability to automatically train and extract features without the need to explicitly define them manually. Deep neural networks are now the dominant classification approach because they automatically extract complex features and have high accuracy. The choice of a specific method depends on the availability of data, resources and requirements for classification accuracy. After classification, it is necessary to determine their specific parameters for objects classified as grains - the fourth stage of the algorithm. These parameters mean the shape of the grain and its geometric dimensions (width and length). The shape of the grain contour reflects the actual shape of the grain.

machine vision, digital identification, grain materials, grain quality, machine learning, post-harvest processing

Full Text:

PDF

1. Kvashuk, D., & Erokhin, R. (2019). Overview of the possibility of mashing approach in agricultural household. Agrosvit, (12), 60 [in English]. https://doi.org/10.32702/2306-6792.2019.12.60

2. Dyatlov, Е. . (2013). Machine vision (analytical review). Mathematical machines and systems, 2, 32–40 [in English].

3. David A. Forsyth & Jean Ponce. (2003). Computer Vision: A Modern Approach. 1 ed. Prentice Hall [in English].

4. Stockman, G., & Shapiro, L. G. (2001). Computer Vision (1st. ed.). Prentice Hall PTR [in English].

5. Haddad, R. A., & Akansu, A. N. (1991). A Class of Fast Gaussian Binomial Filters for Speech and Image Processing. IEEE Transactions on Acoustics, Speech, and Signal Processing, 39, 723–727 [in English].

6. Sobel, I. (2014). History and Definition of the Sobel Operator. [in Ukrainian].

7. Sezgin, M. (2004). Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, 13, 146–165 [in English].

8. Hrytsyk, V. V., & Dunas, А. Ya. (2017). Study of pattern recognition methods for computer vision systems of robots of the future. Information technologies. KhNTU Bulletin, (3 (62)), 297–301. [in Ukrainian].

9. Ryabova, L., Mazur, Y., & Vyshnevska, V. S. (2017). Comparative analysis of binarization methods for images of eye iris. Ukrainian Scientific Journal of Information Security, (23(3)), 171–175 [in English].

10. Kenny's algorithm. (2015, 3 May). Wikipedia. https://uk.wikipedia.org/wiki/Алгоритм_Кенні [in English].

11. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. IJCV, (60 (2)), 91–110[in English].

12. Lowe, D. G. (1999). Object recognition from local scale-invariant features. Proceedings of the International Conference on Computer Vision, 2, 1150–1157 [in English].

13. Bay, H., Tuytelaars, T., & Van Gool, L. (2006). SURF: Speeded up robust features. Proceedings of the 9th European conference on Computer Vision - Volume Part I. [in Ukrainian].

14. Ojala, T., Pietikainen, M., & Maenpaa, M. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987 [in English].

15. Jerebukh, О., & Farmaga, І. (2024). Using neural networks to identify objects in an image. Computer design systems. Theory and practice, 6(1), 232–240. [in Ukrainian].

16. Dhiman, C., & Vishwakarma, D. K. (2019). A review of state-of-the-art techniques for abnormal human activity recognition. Engineering Applications of Artificial Intelligence, 77, 21–45. [in English]. https://doi.org/10.1016/j.engappai.2018.08.014

17. Convolutional neural network (2016). Wikipedia. https://uk.wikipedia.org/wiki/Згорткова_нейронна_мережа [in English].

18. Opitz, D., & Maclin, R. (1999). Popular Ensemble Methods: An Empirical Study. Journal of Artificial Intelligence Research, 11, 169–198. [in English]. https://doi.org/10.1613/jair.614

1. Kvashuk. D., Erokhin. R. Overview of the possibility of mashing approach in agricultural household. Agrosvit. 2019. No. 12. P. 60. URL: https://doi.org/10.32702/2306-6792.2019.12.60.

2. Dyatlov, Е. Machine vision (analytical review). Mathematical machines and systems. 2013. Vol. 2. 32–40.

3. David A. Forsyth, Jean Ponce. Computer Vision: A Modern Approach. 1 ed. Prentice Hall. 2003. 800 p.

4. Stockman G., Shapiro L. G. Computer Vision (1st. ed.). Prentice Hall PTR. 2001. 608 p.

5. Haddad R. A., Akansu A. N. A Class of Fast Gaussian Binomial Filters for Speech and Image Processing. IEEE Transactions on Acoustics, Speech, and Signal Processing. 1991. Vol. 39. P. 723–727.

6. Sobel I. History and Definition of the Sobel Operator. 2014.

7. Sezgin M. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 2004. Vol. 13. P. 146–165.

8. Грицик В. В., Дунас А. Я. Дослідження методів розпізнавання образів для систем комп’ютерного зору роботів майбутнього. Інформаційні технології. Вісник ХНТУ. 2017. № 3 (62). С. 297–301.

9. Ryabova L., Mazur Y., Vyshnevska V. S. Comparative analysis of binarization methods for images of eye iris. Ukrainian Scientific Journal of Information Security. 2017. No. 23(3). P. 171–175.

10. Алгоритм Кенні – Вікіпедія. Вікіпедія. URL: https://uk.wikipedia.org/wiki/Алгоритм_Кенні (дата звернення: 20.10.2024).

11. Lowe D. G. Distinctive image features from scale-invariant keypoints. IJCV. 2004. No. 60 (2). P. 91–110.

12. Lowe D. G. Object recognition from local scale-invariant features. Proceedings of the International Conference on Computer Vision. 1999. Vol. 2. P. 1150–1157.

13. Bay H., Tuytelaars T., Van Gool L. SURF: Speeded up robust features. Proceedings of the 9th European conference on Computer Vision - Volume Part I. 2006.

14. Ojala T., Pietikainen M., Maenpaa M. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002. Vol. 24(7). P. 971–987.

15. Жеребух О., Фармага І. Використання нейронних мереж для визначення об’єктів на зображенні. Computer design systems. Theory and practice. 2024. Т. 6(1). С. 232–240.

16. Dhiman C., Vishwakarma D. K. A review of state-of-the-art techniques for abnormal human activity recognition. Engineering Applications of Artificial Intelligence. 2019. Vol. 77. P. 21–45. URL: https://doi.org/10.1016/j.engappai.2018.08.014.

17. Згорткова нейронна мережа – Вікіпедія. Вікіпедія. URL: https://uk.wikipedia.org/wiki/ Згорткова_нейронна_мережа (дата звернення: 20.10.2024).

18. Opitz D., Maclin R. Popular Ensemble Methods: An Empirical Study. Journal of Artificial Intelligence Research. 1999. Vol. 11. P. 169–198. URL: https://doi.org/10.1613/jair.614

Copyright (c) 2024 Serhii Stepanenko, Viktor Dnesʹ, Andriy Borys, Alvian Kuzmych, Daryna Volyk