Abstract
This work presents a digital image processing technique for the automated visual inspection of glass bottles based on a well-known method used for inspecting aluminium die castings. The idea of this method is to generate median filters adapted to the structure of the object under test. Thus, a “defect-free” reference image can be estimated from the original image of the inspection object. The reference image is compared with the original one, and defects are detected when the difference between them is considerable. The configuration of the filters is performed off-line including a priori information about real defect-free images. In the other hand, the filtering self is performed on-line. Thus, a fast on-line inspection is ensured. According to our experiments, the detection performance in glass bottles was 85% and the false alarms rate was 4%. Additionally, the processing time was only 0.3s/image.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Newman, T., Jain, A.: A survey of automated visual inspection. Computer Vision and Image Understanding 61, 231–262 (1995)
Parker, J.: Defect in glass and their origin. In: First Balkan Conference on Glass Science & Technology, Vollos, Greace (2000)
Firmin, C., Hamad, D., Postaire, J., Zhang, R.: Gaussian neural networks for bottles inspection: a learning procedure. International Journal of Neural System 8, 41–46 (1997)
Hamad, D., Betrouni, M., Biela, P., Postaire, J.: Neural networks inspection system for glass bottles production: A comparative study. International Journal of Pattern Recognition and Artificial Intelligence 12, 505–516 (1998)
Riffard, B., David, B., Firmin, C., Orteu, J., Postaire, J.: Computer vision systems for tuning improvement in glass bottle production: on-line gob control and crack detection. In: Proceedings of the 5th International Conference on Quality Control by Artificial Vision (QCAV-2001), Le Creusot, France (2001)
Mery, D., Jaeger, T., Filbert, D.: A review of methods for automated recognition of casting defects. Insight 44, 428–436 (2002)
Filbert, D., Klatte, R., Heinrich, W., Purschke, M.: Computer aided inspection of castings. In: IEEE-IAS Annual Meeting, Atlanta, USA 1087–1095 (1987)
Castleman, K.: Digital Image Processing. Prentice-Hall, Englewood Cliffs (1996)
Heinrich, W.: Automated Inspection of Castings using X-ray Testing. PhD thesis, Institute for Measurement and Automation, Faculty of Electrical Engineering, Technical University of Berlin (1988) (in German)
Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. John Wiley & Sons, Inc., New York (2001)
Mery, D.: Flaw simulation in castings inspection by radioscopy. Insight 43, 664–668 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mery, D., Medina, O. (2004). Automated Visual Inspection of Glass Bottles Using Adapted Median Filtering. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2004. Lecture Notes in Computer Science, vol 3212. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30126-4_99
Download citation
DOI: https://doi.org/10.1007/978-3-540-30126-4_99
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23240-7
Online ISBN: 978-3-540-30126-4
eBook Packages: Springer Book Archive