Bimodal Model-based 3D Vision and Defect Detection for Free-form Surface Inspection

Christophe Simler, Dirk Berndt, Christian Teutsch

Abstract

This paper presents a 3D vision sensor and its algorithms aiming at automatically detect a large variety of defects in the context of industrial surface inspection of free-form metallic pieces of cars. Photometric stereo (surface normal vectors) and stereo vision (dense 3D point cloud) are combined in order to respectively detect small and large defects. Free-form surfaces introduce natural edges which cannot be discriminated from our defects. In order to handle this problem, a background subtraction via measurement simulation (point cloud and normal vectors) from the CAD model of the object is suggested. This model-based pre-processing consists in subtracting real and simulated data in order to build two complementary “difference” images, one from photometric stereo and one from stereo vision, highlighting respectively small and large defects. These images are processed in parallel by two algorithms, respectively optimized to detect small and large defects and whose results are merged. These algorithms use geometrical information via image segmentation and geometrical filtering in a supervised classification scheme of regions.

References

  1. Chen, S., Li., Y., and Kwok., NM., 2011. Active vision in robotic systems: A survey of recent developments. Int. Journal of Robotics Research, 30(11), 1343-1377.
  2. LaValle, S., 2006. Planning Algorithms, Cambridge University Press, ISBN 0-521-86205-1.
  3. Bishop, C., 2007. Pattern recognition and machine learning, Springer. ISBN: 978-0-387-31073-2.
  4. Simler, C., 2011. An Improved Road and Building Detector on VHR images. IEEE International Geoscience and Remote Sensing Symposium.
  5. Simler, C., Beumier, C., 2010. Building and Road Extraction on Urban VHR Images using SVM Combinations and Mean Shift Segmentation. International Conference on Computer Vision Theory and Applications (VISAPP).
  6. Lu, D., 2004. Change detection techniques. International Journal of remote sensing, 25(12), 2365-2407.
  7. Scarpa, G. and all, 2009. Hierarchical multiple markov chain model for unsupervised texture segmentation. IEEE Trans.on Image Processing 18(8):1830-1843.
  8. Tarabalka and all, 2010. Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognition, 43(7), 2367- 2379.
  9. Debeir, O., Atoui H., Simler, C., 2009. Weakened Watershed Assembly for Remote Sensing Image Segmentation and Change Detection. International Conference on Computer Vision Theory and Applications (VISAPP).
  10. Herbort, S., Wöhler, C., 2011. An Introduction to Imagebased 3D Surface Reconstruction and a Survey of Photometric Stereo Methods. 3D Research, 2:4, 03(2011)4.
  11. Nehab, D., Rusinkiewicz, S., Davis, J., Ramamoorthi, R., 2005. Efficiently combining positions and normals for precise 3d geometry. SIGGRAPH'05, 24(3), 536-543.
  12. Bringier, B., Bony, A., Khoudeir, M., 2012. Specularity and shadow detection for the multisource photometric reconstruction of a textured surface. Journal of the Optical Society of America A, 29(1), 11-21.
  13. Herbort, S. 2014. 3D Shape Measurement and Reflectance Analysis for Highly Specular and InterreflectionAffected Surfaces. Thesis. TUD.
  14. Linden, S., Janz, A., Waske, B., and all., 2007. Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines. J. Appl. Remote Sens., 1(1).
  15. Tsai, D., Hsiao, B., 2001. Automatic surface inspection using wavelet reconstruction. Pattern Recognition, 34, 1285-1305.
  16. Tsai, D., Huang, T., 2003. Automated surface inspection for statistical textures. IVC, 21(4), 307-323.
  17. Henry, Y., Grantham, K., Pang. S., Michael K., 2005. Wavelet based methods on patterned fabric defect detection. Pattern Recognition, 38, 559-576.
  18. Chai, W., Ho, S., Goh, C., 2016. Exploiting sparsity for image-based object surface anomaly detection. IEEE ICASSP.
  19. Lu, C., Shi, J., Jia, J., 2013. Online robust dictionary learning. IEEE Conference CVPR.
  20. Than, D. and all, 2015. Automatic defect detection and the estimation of nominal profiles based on spline for freeform surface parts. IEEE ICAIM.
  21. Su, J., Tarng, Y., 2008. Automated visual inspection for surface appearance defects of varistors using an adaptive neuro-fuzzy inference system. The International Journal of AMT, 25(7), 789-802.
  22. Zheng, H., Kong L., Nahavandi, S., 2002. Automatic inspection of metallic surface defects using genetic algorithms. Journal of MPT, 125-126, 427-433.
  23. Lindner, C., Leon, F., 2007. Model-based segmentation of surfaces using illumination series. IEEE Transactions on Instrumentation and Measurement, 56(4).
Download


Paper Citation


in Harvard Style

Simler C., Berndt D. and Teutsch C. (2017). Bimodal Model-based 3D Vision and Defect Detection for Free-form Surface Inspection . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 451-458. DOI: 10.5220/0006113304510458


in Bibtex Style

@conference{visapp17,
author={Christophe Simler and Dirk Berndt and Christian Teutsch},
title={Bimodal Model-based 3D Vision and Defect Detection for Free-form Surface Inspection},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={451-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006113304510458},
isbn={978-989-758-225-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Bimodal Model-based 3D Vision and Defect Detection for Free-form Surface Inspection
SN - 978-989-758-225-7
AU - Simler C.
AU - Berndt D.
AU - Teutsch C.
PY - 2017
SP - 451
EP - 458
DO - 10.5220/0006113304510458