Real-Time Bottle Quality Control: Comparing Mask R-CNN and YOLOv8x-Seg on an Industrial Conveyor

Mustafa Emad Ahmed; Ahmed A. Thabit; Ali Mahdi Hammadi; Haider W. Oleiwi

doi:10.51173/jt.v8i1.2836

Authors

Mustafa Emad Ahmed Department of Control and Automation Techniques Engineering, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq
Ahmed A. Thabit Department of Electrical Engineering Techniques, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq
Ali Mahdi Hammadi Department of Space Technology Engineering, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq
Haider W. Oleiwi Department of Electronic and Electrical Engineering, Brunel University London, London, United Kingdom

DOI:

https://doi.org/10.51173/jt.v8i1.2836

Keywords:

Machine Vision, Bottle Inspection, YOLOv8x-Seg, Mask R-CNN, IoT-Based Monitoring, PLC Integration

Abstract

Machine Vision (MV) is a computational technology that can independently capture images and analyze them to recognize and interpret their content. to automate visual inspections that were previously performed manually by human inspectors. Automated target recognition is among the key industrial applications of machine vision, and quality assurance on production lines depends heavily on defect detection characterized by speed and accuracy to enhance efficiency and product reliability. This study presents a comparative analysis of two instance-segmentation models, Mask R-CNN and YOLOv8x-Seg, for real-time visual inspection of bottles on industrial conveyor systems. Both models are used to detect multiple attributes, including bottle caps, labels, and liquid levels, with a specific focus on empty bottle detection. When test results are compared, Mask R-CNN is adjudged to have perfect accuracy (100%) at detecting caps, labels, and liquid levels, but has no reliability in the detection of empty bottles. It has processing time of between 0.16 and 0.24 seconds, with the time of inspection on the conveyor belt being 0.265 seconds, which limited the system throughput to 226 bottles per minute at a conveyor speed of 45 cm/s. In contrast, the system has been developed with YOLOv8x-Seg with 100% accuracy in all inspections, including detecting an empty bottle, and has also achieved much lower processing times, from 0.02 to 0.07 seconds. The time of inspection on the conveyor belt is 0.140 seconds. This in turn enhances the performance, which allows the system to run at a higher conveyor speed of 67.5 cm/s with a throughput of 428 bottles per minute and also surpasses previous works. Furthermore, decoupling image acquisition from processing and using an index-based PLC tracking mechanism instead of timer-based synchronization to reject defective bottles from the conveyor belt improves performance and reliability, while IoT technologies enhance production line monitoring, controlling, and productivity under dynamic conditions.

Downloads

Download data is not yet available.

Author Biographies

Mustafa Emad Ahmed, Department of Control and Automation Techniques Engineering, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq

Ahmed A. Thabit, Department of Electrical Engineering Techniques, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq

Ali Mahdi Hammadi, Department of Space Technology Engineering, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq

Haider W. Oleiwi, Department of Electronic and Electrical Engineering, Brunel University London, London, United Kingdom

References

M. Kazmi, B. Hafeez, F. Aftab, J. Shahid, and S. A. Qazi, "A Deep Learning-Based Framework for Visual Inspection of Plastic Bottles," IEEE Access, vol. 11, pp. 125529–125542, 2023, Doi: 10.1109/ACCESS.2023.3329565.

K. J. Pithadiya, C. K. Modi, and J. D. Chauhan, "Machine Vision Based Liquid Level Inspection System using ISEF Edge Detection Technique," in Proc. International Conference and Workshop on Emerging Trends in Technology (ICWET 2010), Mumbai, India, 2010, pp. 601–605.

S. Sathiyamoorthy, "Industrial Application of Machine Vision," International Journal of Research in Engineering and Technology, vol. 3, no. 1, pp. 1–3, Jan. 2014.

V. A. Dave and S. K. Hadia, "Liquid Level and Cap Closure United Inspection using Image Processing," International Journal for Innovative Research in Science & Technology, vol. 1, no. 12, pp. 165–170, May 2015.

M. Hao, H. Yu, and D. Li, "The Measurement of Fish Size by Machine Vision- A Review," in Proc. 9th International Conference on Computer and Computing Technologies in Agriculture (CCTA), Beijing, China, Sep. 2015, pp. 15–32, Doi: 10.1007/978-3-319-48354-2_2.

C. Shah and N. Gund, "Bottling Line Inspection System using Digital Image Processing," Social Science Research Network, 2020.

S. Sridev, P. Karthikeyan, C. A. Prakash, A. Jaganathan, and A. Mani, "Bottle Cap Inspection based on Machine Vision," International Journal of Engineering Research & Technology (IJERT), vol. 5, no. 4, pp. 508–511, Apr. 2016.

N. N. S. Abdul Rahman, N. M. Saad, and A. R. Abdullah, "Shape and Level Bottles Detection Using Local Standard Deviation and Hough Transform," International Journal of Electrical and Computer Engineering, vol. 8, no. 6, pp. 5032–5040, Dec. 2018.

O. Farhangi, E. Sheidaee, and A. Kisalaei, "Machine Vision for Detecting Defects in Liquid Bottles: An Industrial Application for Food and Packaging Sector," Cloud Computing and Data Science, vol. 5, no. 2, pp. 242–254, Jun. 2024.

A. Narayan, C. DK, S. E. Saji, T. Fang, and J. Saniie, "A PyTorch-Based Deep Learning Approach for Enhanced Liquid Level Detection in Industrial Environments," presented at the 2024 IEEE International Conference on Electro Information Technology (EIT), Eau Claire, WI, USA, May 30–Jun. 1, 2024.

R. Deepak Raj, R. Sowmiya, K. Swathi, G. Harikaran, K. Gayathri, A. Ezhil Litta, C. Vishvash, and D. Bharani Kumar, "AI-Driven Automated Quality Inspection for Beverage Bottles: Leveraging Object Detection Models for Enhanced Supply Chain Efficiency," International Journal of Innovative Science and Research Technology, vol. 10, no. 3, pp. 2773–2782, Mar. 2025, Doi: 10.38124/ijisrt/25mar1796.

M. Mikhail and K. Abad, "Robotic inspection and automated analysis system for advanced manufacturing," IAES International Journal of Robotics and Automation (IJRA), vol. 12, no. 4, pp. 352–364, Dec. 2023.

U. Kaewmorakot, L. Poolperm, P. Prongphimai, and S. Tansriwong, "The development of a prototype of an automated bottle caps visual inspection system," presented at the International Electrical Engineering Congress (iEECON), Khon Kaen, Thailand, Mar. 9–11, 2022.

P. Petru, "What is Mask R-CNN? The ultimate guide," Roboflow Blog, Aug. 9, 2023. [Online]. Available: https://blog.roboflow.com/mask-rcnn/.et al.

R. Girshick, "Fast R-CNN," in Proc. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015.

S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in Advances in Neural Information Processing Systems 28 (NeurIPS), Montreal, QC, Canada, 2015.

K. He, G. Gkioxari, P. Dollár, and R. Girshick, "Mask R-CNN," in Proc. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017.

Glenn-Jocher, "summary of YOLOv8-Seg model structure," GitHub, Mar. 29, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics/issues/1710.

Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, "Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression," in Proc. 34th AAAI Conference on Artificial Intelligence (AAAI-20), New York, NY, USA, 2020.

Z. Tian, C. Shen, and H. Chen, "Conditional Convolutions for Instance Segmentation," in Computer Vision – ECCV 2020, Cham: Springer International Publishing, 2020.