Abstract
Quality inspection is an essential technology in the glass product industry. Machine vision has shown more significant potential than manual inspection at present. However, the visual inspection of the bottle for defects remains a challenging task in a quality-controlled due to the difficulty in detecting some notable defects. To overcome the problem, we propose a surface defect detection framework based on the stripe light source. First, a novel method, DTST, determines the stripe type in the background with traditional image processing methods. Then, according to the result of DTST, the stripe type is divided into vertical stripes and horizontal stripes. For the former, a defect detection method based on DDVS that uses machine learning technology is proposed to detect cold mold defects precisely. A defect detection method named DDHS that uses deep learning technology is proposed to precisely detect wrinkled skin defects for the latter. The proposed framework is tested for data sets obtained by our designed vision system. The experimental results demonstrate that our framework achieves good performance.
Supported by organization x.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rahman, A.: Shape and level bottles detection using local standard deviation and hough transform. Int. J. Electr. Comput. Eng. (IJECE) 8(6) (2018)
Xin, Z.: An improve feature selection algorithm for defect detection of glass bottles. Appl. Acoust. 174 (2021). (in Chinese)
Fu, L.: Medicine glass bottle defect detection based on machine vision. In: Chinese Control And Decision Conference. Nanchang, China 2019, pp. 5681–5685 (2019). (in Chinese)
Yexin, Z.: Bottle body detection algorithm and application in high speed high accuracy empty bottle detection robot. Hunan University (2017). (in Chinese)
Tian, B.: Glassware defect detection system based on machine vision. Shandong University (2018). (in Chinese)
Wei, J.: Inspection of medicinal glass bottle’s dimension and defect based on machine vision. Chongqing University of Technology (2012). (in Chinese)
We, Z.: Classification and recognition method for bearing fault based on IFOA-SVM. Mech. Transm. 45(02), 148–156 (2021). (in Chinese)
Krizhevsky, A.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105. Curran Associates Inc. (2012)
Acknowledgement
This study is supported by the key research project of the Ministry of Science and Technology (Grant No. 2018YFB1306802) the National Natural Science Foundation of China (Grant No. 51975344) and China Postdoctoral Science Foundation (Grant No. 2019M662591).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, J., Zhang, X., Li, C. (2021). An Surface Defect Detection Framework for Glass Bottle Body Based on the Stripe Light Source. In: Liu, XJ., Nie, Z., Yu, J., Xie, F., Song, R. (eds) Intelligent Robotics and Applications. ICIRA 2021. Lecture Notes in Computer Science(), vol 13014. Springer, Cham. https://doi.org/10.1007/978-3-030-89098-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-89098-8_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89097-1
Online ISBN: 978-3-030-89098-8
eBook Packages: Computer ScienceComputer Science (R0)