Optimal Gabor Filters and Haralick Features for the Industrial Polarization Imaging

  • Yannick Caulier
  • Christophe Stolz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6930)

Abstract

During the past decade, computer vision methods for inline inspection became an important tool in a lot of industrial processes. During the same time polarization imaging techniques rapidly evolved with the development of electro-optic components, as e.g. the polarization cameras, now available on the market. This paper is dedicated to the application of polarization techniques for visually inspecting complex metallic surfaces. As we will shortly recall, this consists of a direct image interpretation based on the measurement of the polarization parameters of the light reflected by the inspected object. The proposed image interpretation procedure consists of a Gabor pre-filtering and a Haralick feature detector. It is demonstrated that polarization images permit to reach higher classification rates than in case of a direct interpretation of images without polarization information.

Keywords

Direct Interpretation Pixel Pair Polarization Image Stokes Vector Polarization Information 
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. [Caulier and Bourennane, 2010]
    Caulier, Y., Bourennane, S.: Visually inspecting specular surfaces: A generalized image capture and image description approach. IEEE Transactions on Pattern Analysis and Machine Intelligence (2010)Google Scholar
  2. [Chengjun and Wechsler, 2003]
    Chengjun, L., Wechsler, H.: Independent component analysis of gabor features for face recognition. IEEE Trans. on Neural Networks 14(4), 919–928 (2003)CrossRefGoogle Scholar
  3. [Daugman, 1985]
    Daugman, J.: Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filter. Optical Society of America 2, 1160–1169 (1985)CrossRefGoogle Scholar
  4. [Dunn, 1995]
    Dunn, D.: Optimal gabor filters for texture segmentation. IEEE Trans. in Image Processing 7(4), 947–964 (1995)CrossRefGoogle Scholar
  5. [Goldstein, 2003]
    Goldstein, D.: Polarized Light (2003)Google Scholar
  6. [Kovesi, 2011]
    Kovesi, P.D.: Matlab and octave functions for computer vision and image processing (2011), http://www.csse.uwa.edu.au/~pk/Research/MatlabFns
  7. [Morel et al., 2006]
    Morel, O., Stolz, C., Meriaudeau, F., Gorria, P.: Active lighting applied to 3d reconstruction of specular metallic surfaces by polarization imaging. Applied Optics 45(17), 4062–4068 (2006)CrossRefGoogle Scholar
  8. [Porebski, 2008]
    Porebski, A.V.N.M.L.: Haralick feature extraction from lbp images for color texture classification. In: First Workshops on Image Processing Theory, Tools and Applications, IPTA 2008, pp. 1–8 (2008)Google Scholar
  9. [Terrier et al., 2008]
    Terrier, P., Devlaminck, V., Charbois, J.-M.: Segmentation of rough surfaces using a polarization imaging system. Journal of the Optical Society America 25(2), 423–430 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Yannick Caulier
    • 1
  • Christophe Stolz
    • 2
  1. 1.Fraunhofer Institute for Integrated Circuits.ErlangenGermany
  2. 2.Laboratoire Electronique Informatique et Image.Le CreusotFrance

Personalised recommendations