Authors : Deepak Raj R; Sowmiya R; Swathi K; Harikaran G; Gayathri K; Ezhil Litta A; Vishvash C; Bharani Kumar Depuru

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/42s28waw

Scribd : https://tinyurl.com/4be5tw4c

DOI : https://doi.org/10.38124/ijisrt/25mar1796

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : In the beverage industry, maintaining product quality during packaging and throughout the supply chain is critical to ensuring customer satisfaction and brand integrity. This research addresses the challenge of automating quality inspection for beverage bottles by leveraging cutting-edge AI-based object detection models. The study focuses on identifying and classifying six key quality defects particularly Cracked_Bottle, Misaligned_Label, Missing_Cap, Normal_ Bottle, Overfilled_Bottle, and Underfilled_Bottle. These defects, if undetected, can lead to customer dissatisfaction, increased return rates, and potential brand damage. To tackle this problem, we implemented and evaluated three advanced object detection architectures— YOLOv8, YOLOv9, and YOLOv11—on a custom dataset comprising thousands of images of beverage bottles captured under diverse conditions, including varying lighting, angles, and backgrounds. Among the models, YOLOv8 emerged as the most effective, achieving an impressive 78% accuracy across all defect classes. The model demonstrated exceptional performance in detecting subtle defects such as misaligned labels and minor cracks, which are often overlooked in manual inspections. The integration of AI-driven quality control systems into the beverage supply chain not only minimizes human error but also significantly enhances operational efficiency. By automating the detection of defects, this approach ensures that only products meeting stringent quality standards reach consumers. Furthermore, the system provides real-time feedback, enabling swift corrective actions and reducing waste. This research underscores the transformative potential of AI in revolutionizing quality assurance processes within the beverage industry, ultimately driving customer trust, reducing costs, and improving overall supply chain performance.

Keywords : Beverage Quality Assurance, Defect Detection, Yolov8, Yolov9, Yolov11, AI In Packaging, Supply Chain Optimization, Automated Quality Inspection.

References :

1. Studer, S.; Bui, T.B.; Drescher, C.; Hanuschkin, A.; Winkler, L.; Peters, S.; Müller, K.-R. Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology. Mach. Learn. Knowl. Extr. 2021, 3, 392-413. https://doi.org/10.3390/make3020020
2. Y. Li and Y. Zhang, "Application Research of Computer Vision Technology in Automation," 2020 International Conference on Computer Information and Big Data Applications (CIBDA), Guiyang, China, 2020, pp. 374-377. https://doi.org/10.1109/CIBDA50819.2020.00090.
3. Congcong Wang, Xiumei Wei, Xuesong Jiang, An automated defect detection method for optimizing industrial quality inspection, Engineering Applications of Artificial Intelligence, Volume 127, Part B, 2024, 107387, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2023.107387
4. Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement.
   arXiv preprint arXiv:1804.02767.
   https://doi.org/10.48550/arXiv.1804.02767
5. Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection.
   arXiv preprint arXiv:2004.10934.
   https://doi.org/10.48550/arXiv.2004.10934
6. Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.
   arXiv preprint arXiv:2207.02696.
   https://doi.org/10.48550/arXiv.2207.02696
7. Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., ... & Zitnick, C. L. (2014). Microsoft COCO: Common Objects in Context.
   In European conference on computer vision (pp. 740-755). Springer, Cham.
   https://doi.org/10.48550/arXiv.1405.0312
8. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition.
   In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
   https://doi.org/10.48550/arXiv.1512.03385
9. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
   arXiv preprint arXiv:1704.04861.
   https://doi.org/10.48550/arXiv.1704.04861
10. Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.
    In International Conference on Machine Learning (pp. 6105-6114). PMLR.
    https://doi.org/10.48550/arXiv.1905.11946
11. Shorten, C., Khoshgoftaar, T.M. A survey on Image Data Augmentation for Deep Learning. J Big Data 6, 60 (2019). https://doi.org/10.1186/s40537-019-0197-0
12. Everingham, M., Van Gool, L., Williams, C.K.I. et al. The Pascal Visual Object Classes (VOC) Challenge. Int J Comput Vis 88, 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4
13. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.
    In Advances in neural information processing systems (pp. 91-99).
    https://doi.org/10.48550/arXiv.1506.01497
14. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation.
    In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587).
    https://doi.org/10.48550/arXiv.1311.2524
15. Ali, U., Maizatul Akmar Ismail, Riyaz Ahamed Ariyaluran Habeeb, & Syed Roshaan Ali Shah. (2024). Performance Evaluation of YOLO Models in Plant Disease Detection. Journal of Informatics and Web Engineering, 3(2), 199–211. https://doi.org/10.33093/jiwe.2024.3.2.15