dihedral groups and spatio chromatic filter systems
play

Dihedral Groups and Spatio-Chromatic Filter Systems Reiner Lenz, - PowerPoint PPT Presentation

Dihedral Groups and Spatio-Chromatic Filter Systems Reiner Lenz, Martin Solli Linkping University reiner.lenz@liu.se; martin.solli@liu.se FWS-2010-Ilmenau Reiner Lenz Take-Home-Message Can you see the irreducible representations of


  1. Dihedral Groups and Spatio-Chromatic Filter Systems Reiner Lenz, Martin Solli Linköping University reiner.lenz@liu.se; martin.solli@liu.se FWS-2010-Ilmenau Reiner Lenz

  2. Take-Home-Message Can you see the irreducible representations of dihedral groups? Can you hear the shape of a drum? Feynman FWS-2010-Ilmenau Reiner Lenz

  3. The Algebra of Digital Color Images 1. Algebra, Filter design from first principles 2. Visual properties of filters 3. Discrimination of visual classes, Image retrieval, Emotions FWS-2010-Ilmenau Reiner Lenz

  4. Digital Color Images • Consists of pixels • Pixels are located on a grid • Pixel value is a 3-D vector FWS-2010-Ilmenau Reiner Lenz

  5. What can we do with them? Transform the grid k ● 90 degree rotation reflection on diagonal Form the group D(4) FWS-2010-Ilmenau Reiner Lenz

  6. What can we do with them? Transform the channels B k ● 120 degree rotation reflection on symmetry axis Form the group D(3) = S(3) permutation group R G FWS-2010-Ilmenau Reiner Lenz

  7. Dimensionality of Pattern Space Take N points invariant under D(4) and the 3 color channels invariant under D(3) Coordinates are (x,c) = (position, channel) The possible value distributions form a 3N – dimensional space P P of patterns p(x,c) This space is invariant under D(4) and D(3) Rot, Green = 12 Blue = 24 RGB = 48 FWS-2010-Ilmenau Reiner Lenz

  8. Decomposition of Pattern Space Representation theory of finite groups: The space can be split into invariant subspaces of minimum dimension P = P 0 + P 1 + … + P K P = P 0 + P 1 + … + P K p = (a 01 b 01 + … + a 0k(0) b 0k(0) ) + … + (a K1 b K1 + … + a Kk(K) b Kk(K) ) a kl = p’b kl a kl are coefficients, b kl are “basis patterns” FWS-2010-Ilmenau Reiner Lenz

  9. Some Properties The spaces P P k have dimensions 1, 2 or 4 The “basis patterns” or “filter functions” consist of 0,1 and -1 The “feature vectors ” ( a n1 …a nk(n) ) have simple transformation properties under D(4)xD(3) transformations of the pattern p (steerable filters) The norm of the “feature vectors ” r n = ||( a n1 …a nk(n) )|| is invariant under D(4)xD(3) transformations FWS-2010-Ilmenau Reiner Lenz

  10. Simplest example: 2x2 Color Channels 2x2 = 4 pixels 3x4 = 12 dimensionial vectors p Step 1: Combine channels in R+G+B and (2-D vector (R-G,R+G-2B) FWS-2010-Ilmenau Reiner Lenz

  11. Spatial - Intensity four pixel vector with intensity values is multiplied by The first is an averaging filter (1D subspace) The second is a line filter (1D subspace) The third+fourth are x- and y-gradients (2D subspace) FWS-2010-Ilmenau Reiner Lenz

  12. Spatial – Color Channels 4 pixels and 2 channels = 8 – dimensional vector Theory gives the decomposition in invariant subspaces of dimensions up to four FWS-2010-Ilmenau Reiner Lenz

  13. Implementation Compute + + + - + + + - This is the “FFT” form of the computation FWS-2010-Ilmenau Reiner Lenz

  14. 4x4 Window 4x4x3 = 48 dimensions FWS-2010-Ilmenau Reiner Lenz

  15. Signatures From 4x4x3 = 48D RGB distribution Compute 48 new features (multiplication with a square matrix) Collect the 48 features in 24 sub-vectors For every sub-vector compute the norms r 1 … r 24 These 24 norms are collected in the signature vector FWS-2010-Ilmenau Reiner Lenz

  16. Application to Image Retrieval Databases: Real-world databases from Picsearch search engine a) Objects like beach Monet and Warhol 320 000 images b) Emotions like colorful and elegant 1.2 million images Download at http://diameter.itn.liu.se/emodb FWS-2010-Ilmenau Reiner Lenz

  17. Descriptors 1. An image consists of B blocks of size 4x4 2. Every block gives a 24D signature vector 3. Describe the image by the histograms over these signature vectors FWS-2010-Ilmenau Reiner Lenz

  18. Characteristic Images Intensity line 2x2 FWS-2010-Ilmenau Reiner Lenz

  19. Intensity Edge FWS-2010-Ilmenau Reiner Lenz

  20. Color Edge FWS-2010-Ilmenau Reiner Lenz

  21. Homogeneous Color FWS-2010-Ilmenau Reiner Lenz

  22. Visual properties of Colorful/Elegant FWS-2010-Ilmenau Reiner Lenz

  23. Training of Support-Vector-Machines for two-class discrimination Use different combinations of signature vectors train a SVM with half of the data and two classes Use the output of the SVM as indicator of the class membership FWS-2010-Ilmenau Reiner Lenz

  24. Warhol-Monet FWS-2010-Ilmenau Reiner Lenz

  25. Intensity-Line-2x2 FWS-2010-Ilmenau Reiner Lenz

  26. FWS-2010-Ilmenau Reiner Lenz Edge-Intensity-2x2

  27. FWS-2010-Ilmenau Reiner Lenz Homogeneous color 2x2

  28. FWS-2010-Ilmenau Reiner Lenz Color Edge 2x2

  29. FWS-2010-Ilmenau Reiner Lenz All Color

  30. FWS-2010-Ilmenau Reiner Lenz Colorful-Elegant

Recommend


More recommend