基于机器视觉的金属包装表面损伤检测改进方法
An Improved Damage Detection Method for Metal Packaging Surfaces Based on Machine Vision
摘要: 金属印刷包装盒作为用于储存食品、药品等物品的容器，其表面质量需要受到严格控制，以满足相关质量要求。由于人工检测存在效率低、主观性强和稳定性不足等问题，因此有必要开发自动化检测系统。本文提出了一种非接触式高精度表面缺陷检测方法，用于检测和识别金属印刷包装盒表面缺陷。针对图像处理过程中容易产生影响缺陷识别的图像伪影问题，本文引入超分辨率重建技术，以提高图像获取与处理质量。同时，采用曲线拟合方法对测试图像中的感兴趣区域进行特征提取。最终，实现了图像缺陷特征的提取与识别。实验结果表明，该方法能够在有限相机分辨率条件下显著提高图像配准精度，并可检测宽度细至0.08 mm的划痕缺陷，能够满足印刷厂实际生产中的检测需求。
Abstract: Metal printed packaging box, a container known to store food, medicine and other items, should be controlled to meet the requirements of surface quality. Due to the problems of manual detection, it is necessary to develop an automated detection system. In this paper, a non-contact high-precision surface defect detection method for detecting and identifying surface defects of metal printing packaging boxes is developed. In this regard, since image artifacts often occur in the image processing process that affect the identification of defects, some innovative actions have been taken, super-resolution reconstruction techniques, to determine the method of obtaining appropriate images. Also, feature extraction is conducted on the region of interest in the test image, utilizing curve fitting. Ultimately, image defect features are extracted and subsequently identified. Experimental results demonstrate that this method markedly enhances image registration accuracy under limited camera resolution, capable of detecting scratches as fine as 0.08 mm. This method adequately fulfills the practical detection needs of printing plants.
文章引用：马俊杰, 陶冠霖, 潘大宝, 杨继新, 吕庆佳, 王鹏, 刘阳. 基于机器视觉的金属包装表面损伤检测改进方法[J]. 人工智能与机器人研究, 2026, 15(3): 953-967. https://doi.org/10.12677/airr.2026.153087

参考文献

[1] Yu, Z., Wu, X. and Gu, X. (2017) Fully Convolutional Networks for Surface Defect Inspection in Industrial Environment. In: Liu, M., Chen, H. and Vincze, M., Eds., Computer Vision Systems, Springer, 417-426. [Google Scholar] [CrossRef] 
[2] Konovalenko, I., Maruschak, P. and Brevus, V. (2021) Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks. Journal of Computing and Information Science in Engineering, 22, Article ID: 014501. [Google Scholar] [CrossRef] 
[3] Liu, Q., Wang, C., Li, Y., Gao, M. and Li, J. (2022) A Fabric Defect Detection Method Based on Deep Learning. IEEE Access, 10, 4284-4296. [Google Scholar] [CrossRef] 
[4] Lamb, J., Echlin, M., Polonsky, A., Geurts, R., Pusch, K., Raeker, E., et al. (2022) Merging Machine Learning and Tribeam Tomography for 3D Defect Detection in an AM Coni-Based Superalloy. Microscopy and Microanalysis, 28, 862-863. [Google Scholar] [CrossRef] 
[5] Bouzenad, A.E., Yaacoubi, S., Montresor, S. and Bentahar, M. (2022) A Model-Based Approach for In-Situ Automatic Defect Detection in Welds Using Ultrasonic Phased Array. Expert Systems with Applications, 206, Article ID: 117747. [Google Scholar] [CrossRef] 
[6] Nayak, J.P.R. and Parameshachari B. D., (2022) Defect Detection in Printed Circuit Boards Using Leaky-Lenet 5. International Journal of Software Innovation, 10, 1-13. [Google Scholar] [CrossRef] 
[7] Vu, T., Pham, D. and Chang, T. (2023) A Yolo-Based Real-Time Packaging Defect Detection System. Procedia Computer Science, 217, 886-894. [Google Scholar] [CrossRef] 
[8] Suresh, B.R., Fundakowski, R.A., Levitt, T.S. and Overland, J.E. (1983) A Real-Time Automated Visual Inspection System for Hot Steel Slabs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5, 563-572. [Google Scholar] [CrossRef] [PubMed]
[9] Gupta, G. (2011) Algorithm for Image Processing Using Improved Median Filter and Comparison of Mean, Median and Improved Median Filter. International Journal of Soft Computing Engineering, 1, 304-311.
[10] Lee, J., Shim, S., You, B. and Hwang, D. (2014) Design of Line Scratch Detection and Restoration Algorithm Using GPU. Journal of the Korea Society of Computer and Information, 19, 9-16. [Google Scholar] [CrossRef] 
[11] Li, K.B., Yu, H.Y. and Zhou, S.J. (2018) Surface Scratch Detection of Mechanical Parts Based on Morphological Features. Acta Optica Sinica, 38, Article ID: 0815027. [Google Scholar] [CrossRef] 
[12] Ding, W., Wang, Q. and Zhu, J. (2020) Automatic Detection of Dispersed Defects in Resin Eyeglass Based on Machine Vision Technology. IEEE Access, 8, 44661-44670. [Google Scholar] [CrossRef] 
[13] Mar, N.S.S., Yarlagadda, P.K.D.V. and Fookes, C. (2011) Design and Development of Automatic Visual Inspection System for PCB Manufacturing. Robotics and Computer-Integrated Manufacturing, 27, 949-962. [Google Scholar] [CrossRef] 
[14] Barua, S., Liou, F., Newkirk, J. and Sparks, T. (2014) Vision-Based Defect Detection in Laser Metal Deposition Process. Rapid Prototyping Journal, 20, 77-85. [Google Scholar] [CrossRef] 
[15] He, P., Sun, X. and Zhou, G. (2020) Defect Detection of Energized Grid Based on Machine Vision. 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP), Nanjing, 23-25 October 2020, 376-380. [Google Scholar] [CrossRef] 
[16] Colvalkar, A., Pawar, S.S. and Patle, B.K. (2023) In-pipe Inspection Robotic System for Defect Detection and Identification Using Image Processing. Materials Today: Proceedings, 72, 1735-1742. [Google Scholar] [CrossRef] 
[17] Liu, G. and Zheng, X. (2021) Fabric Defect Detection Based on Information Entropy and Frequency Domain Saliency. The Visual Computer, 37, 515-528. [Google Scholar] [CrossRef] 

为你推荐