Machine vision system for surface inspection on brushed industrial parts
Abstract
This work aims at detecting defects on metallic industrial parts with streaked surface. The orientation of those parallel streaks is totally random. The searched defects are scratch and lack of machining. A specific machine vision system has been designed to deal with the particular inspected surface features. One image is acquired with an annular lighting in bright field and six images are acquired with a rotating lighting in dark field. A particular image processing is applied on the six images in order to get one image that represents all the revealed imperfections. A thresholding processing is then applied on this image in order to segment the imperfections. A trained classification, created with well known typical objects of each class, is performed. The classification has to recognize the different defects and the small imperfections that are not defects. The decision phase is used to know if the defects are acceptable, and therefore if the inspected part is acceptable. Some acceptability rules are defined for every defect class. The developed machine vision system has been implemented on an experimental industrial production line and it gives 2% of sub-detection and 16% of over-detection.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
A survey on industrial vision systems, applications and tools
Malamas, E. N., Petrakis, E. G. M., Zervakis, M. E., Petit, L., & Legat, J.-D. (2003) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00152-x · Cited by 798 · see citing works
Reliable tool wear monitoring by optimized image and illumination control in machine vision
Pfeifer, T., & Wiegers, L. (2000) · Measurement · doi:10.1016/s0263-2241(00)00014-2 · Cited by 138 · see citing works
Image acquisition techniques for automatic visual inspection of metallic surfaces
Pernkopf, F., & O'Leary, P. (2003) · NDT & E International · doi:10.1016/s0963-8695(03)00081-1 · Cited by 117 · see citing works
Real-time Industrial Visual Inspection: A Review
Thomas, A., Rodd, M. G., Holt, J. D., & Neill, C. J. (1995) · Real-Time Imaging · doi:10.1006/rtim.1995.1014 · Cited by 72 · see citing works
Seulin, R., Merienne, F., & Gorria, P. (2002) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/s1110865702203030 · Cited by 25 · see citing works
Self-citationSVM approximation for real-time image segmentation by using an improved hyperrectangles-based method
Mitéran, J., Bouillant, S., & Bourennane, E. (2003) · Real-Time Imaging · doi:10.1016/s1077-2014(03)00035-4 · Cited by 14 · see citing works
Machine vision systems in the metallurgy industry
Legrand, A.-C., Suzeau, P., Renier, E., et al. (2001) · Journal of Electronic Imaging · doi:10.1117/1.1314334 · Cited by 10 · see citing works
Seulin, R., Bonnot, N., Merienne, F., et al. (2002) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.455250 · Cited by 6 · see citing works
Self-citationDefect detection and classification on metallic parts
Bourgeat, P., & Mériaudeau, F. (2002) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.460196 · Cited by 3 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Automated Visual Defect Classification for Flat Steel Surface: A Survey
Luo, Q., Fang, X., Su, J., Zhou, J., Zhou, B., Yang, C., Liu, L., Gui, W., & Tian, L. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3030167 · Cited by 148 · see citing works
- Authors
- Bonnot, N., Seulin, R., & Merienne, F.
- Affiliations
- Université de Bourgogne (FR)
- Venue
- SPIE Proceedings
- Publisher
- SPIE
- Published
- 2004-05-03
- Volume
- 5303
- Pages
- 64
- ISSN
- 0277-786X (ISSN-L)
- OpenAlex
- W2007562878
- Cited by
- 13
- References
- 9
- Citations by year
- 2026: 1 · 2024: 1 · 2021: 1 · 2020: 1 · 2017: 1 · 2016: 1 · 2015: 1 · 2014: 1
- FWCI
- 2.24
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (publishedVersion)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
- Physical Sciences › Engineering › Computational Mechanics › Surface Roughness and Optical Measurements
- Keywords
- machine vision, surface inspection, defect detection, scratch defects, dark-field imaging, binarization, image segmentation, defect classification, industrial production lines
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
