Kemerovo, Russian Federation
Kemerovo, Russian Federation
Kemerovo, Russian Federation
Kemerovo, Russian Federation
Kemerovo, Russian Federation
Artificial intelligence can be used to monitor production parameters in the food industry. Kissel is a jelly-like fruit or berry starch drink. Instant kissel usually consists of granules. Neural networks may help to control the size of kissel granules. In this research, convolutional neural networks monitored the production parameters of granulated kissel powder by localizing granules in an image. Size is the most important parameter of kissel granules: it should remain between 2 and 5 mm. To detects larger granules (≥ 5 mm), the network was provided with a visual dataset of granules of varying sizes. The localization models were developed using Detectron2. The research yielded a set of optimal operating principles and quality metrics. The R50-FPN model achieved the best results. The AP50 metric had the highest value, followed by AP75 and AP. The models performed well in visual detection and successfully determined the coordinates of the bounding rectangle. The resulting dataset did not label objects for small (APs) and medium (APm) sizes because the study focused on localizing large granules. The APl metric values for all models were high. The approach to AI training and neural network architecture proved optimal for food production control. The trained model made it possible to develop a computer program based on convolutional neural networks that demonstrated good results in detecting large granules in instant kissel powder. The new program can be used in continuous production to monitor the size of finished products and their compliance with process parameters.
Artificial intelligence, neural networks, localization, granulated products, granulated kissel
1. Shafrai AV, Permyakova LV, Borodulin DM, Sergeeva IY. Modeling the physiological parameters of brewer’s yeast during storage with natural zeolite-containing tuffs using artificial neural networks. Information. 2022;13(11):529. https://doi.org/10.3390/info13110529
2. Korolev IA. Automated measurement of air bubbles dispersion in ice cream using machine learning methods. Food Processing: Techniques and Technology. 2023;53(3):455–464. (In Russ.) https://doi.org /10.21603/2074-9414-2023-3-2448
3. Jo DM, Han S-J, Ko S-C, Kim KW, Yang D, et al. Application of artificial intelligence in the advancement of sensory evaluation of food products. Trends in Food Science & Technology. 2025;165:105283. https://doi.org/10.1016/j.tifs.2025.105283
4. Mikheev PN. Artificial intelligence technologies in the food industry. Innovation & Investment. 2023;(4):536–539. (In Russ.) https://elibrary.ru/DYOHTS
5. Lyndina MI. Ways to improve the food industry. Material assets for government needs: Innovative production and storage. 2020;(13):157–163. (In Russ.) https://elibrary.ru/DHQPUP
6. Popov AM. Granulated beverage concentrates: Technological analysis and synthesis. Kemerovo: KemTIPP; 2003. pp. 133–148. (In Russ.)
7. Ksenofontov VV. Neural networks. Problems of science. 2020;(11):28–29. (In Russ.) https://elibr ary.ru/DTVJNS
8. Hassan E, El-Rashidy N, Talaat FM. Mask R-CNN models. Nile Journal of Communication and Computer Science. 2022;3(1):17–27. https://doi.org/10.21608/njccs.2022.280047
9. Olorunshola OE, Jemitola PO, Ademuwagun A. Comparative study of some deep learning object detection algorithms: R-CNN, fast R-CNN, faster R-CNN, SSD, and YOLO. Nile Journal of Engineering and Applied Science. 2023;1(1):70–80. https://doi.org/10.5455/NJEAS.150264
10. Prakash SR, Singh PN. Object detection through region proposal based techniques. Materials Today: Proceedings. 2021;46(9):3997–4002. https://doi.org/10.1016/j.matpr.2021.02.533
11. Zhu L, Lee F, Cai J, Yu H, Chen Q. An improved feature pyramid network for object detection. Neurocomputing. 2022;483:127–139. https://doi.org/10.1016/j.neucom.2022.02.016
12. Xavier AI, Villavicencio C, Macrohon JJ, Jeng J-H, Hsieh J-G. Object detection via gradient-based mask R-CNN using machine learning algorithms. Machines. 2022;10(5):340. https://doi.org/10.3390/machines10050340
13. Jabir B, Falih N, Rahmani K. Accuracy and efficiency comparison of object detection open-source models. International Journal of Online and Biomedical Engineering. 2021;17(5):165–184. https://doi.org/10.3991/ijoe.v17i05.21833
14. Peng H, Yu S. A systematic IOU-related method: Beyond simplified regression for better localization. IEEE Transactions on Image Processing. 2021;30:5032–5044. https://doi.org/10.1109/TIP.2021.3077144
