Advertisement

A Combinatorial Transparent Surface Modeling from Polarization Images

  • Mohamad Ivan Fanany
  • Kiichi Kobayashi
  • Itsuo Kumazawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3322)

Abstract

This paper presents a combinatorial (decision tree induction) technique for transparent surface modeling from polarization images. This technique simultaneously uses the object’s symmetry, brewster angle, and degree of polarization to select accurate reference points. The reference points contain information about surface’s normals position and direction at near occluding boundary. We reconstruct rotationally symmetric objects by rotating these reference points.

Keywords

Zenith Angle Reference Vector Brewster Angle Polarization Image Ambiguity Problem 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Szeliski, R.: From images to models (and beyond): a personal retrospective. In: Vision Interface 1997, Kelowna, British Columbia, pp. 126–137. Canadian Image Processing and Pattern Recognition Society (1997)Google Scholar
  2. 2.
    Miyazaki, D., Kagesawa, M., Ikeuchi, K.: Transparent Surface Modeling from a Pair of Polarization Images. IEEE Trans. on PAMI 26(1), 73–82 (2004)Google Scholar
  3. 3.
    Miyazaki, D., Saito, M., Sato, Y., Ikeuchi, I.: Determining Surface Orientations of Transparent Objects Based on Polarization Degrees in Visible and Infrared Wavelength. J. Opt. Soc. Am. A 19(4), 687–694 (2002)CrossRefGoogle Scholar
  4. 4.
    Rahmann, S., Centerakis, N.: Reconstruction of Specular Surfaces Using Polarization Imaging. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 246–253 (2001)Google Scholar
  5. 5.
    Saito, M., Sato, Y., Ikeuchi, K., Kashiwagi, H.: Measurement of surface orientation of transparent objects by use of polarization in highlight. J. Opt. Soc. Am. A 16(9), 2286–2293 (1999)CrossRefGoogle Scholar
  6. 6.
    Nayar, S.K., Ikeuchi, K., Kanade, T.: Determining Shape and Reflectance of Hybrid Surface by Photometric Sampling. IEEE Trans. Robotics and Automation 6(4), 418–431 (1990)CrossRefGoogle Scholar
  7. 7.
    Mitsumoto, H., Tamura, S., Okazaki, K., Fukui, Y.: Reconstruction using mirror images based on a plane symmetry recovery method. IEEE Trans. on PAMI 14, 941–946 (1992)Google Scholar
  8. 8.
    Zabrodsky, H., Peleg, S., Avnir, D.: Symmetry as a continuous feature. IEEE Trans. on PAMI 17, 1154–1156 (1995)Google Scholar
  9. 9.
    Liu, Y., Rothfus, W., Kanade, T.: Content-based 3d neororadiologic image retrieval: Preliminary results. In: IEEE International Workshop on Content-based Access of Image and Video Databases, January 1998, pp. 91–100 (1998)Google Scholar
  10. 10.
    Leou, J., Tsai, W.: Automatic rotational symmetry determination for shape analysis. Pattern Recognition 20, 571–582 (1987)CrossRefGoogle Scholar
  11. 11.
    Wolfson, H., Reisfeld, D., Yeshurun, Y.: Robust facial feature detection using symmetry. In: Proc. of Int. Conf. on Pattern Recognition, pp. 117–120 (1992)Google Scholar
  12. 12.
    Quinlan, J.R.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar
  13. 13.
    Yuan, Y., Shaw, M.J.: Induction of fuzzy decision trees. Fuzzy Sets System 69, 125–139 (1995)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Horn, B.K.P.: Height and Gradient from Shading. International Journal of Computer Vision 5(1), 37–75 (1990)CrossRefGoogle Scholar
  15. 15.
    Miyazaki, D., Tan, R.T., Hara, K., Ikeuchi, K.: Polarization-based Inverse Rendering from Single View. In: Proc. International Symposium on CREST Digital Archiving Project, Tokyo, pp. 51–65 (2003)Google Scholar
  16. 16.

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Mohamad Ivan Fanany
    • 1
  • Kiichi Kobayashi
    • 1
  • Itsuo Kumazawa
    • 2
  1. 1.NHK Engineering Service Inc.TokyoJapan
  2. 2.Imaging Science and EngineeringTokyo Institute of Technology 

Personalised recommendations