Advertisement

Modeling Shapes with Higher-Order Graphs: Methodology and Applications

  • Chaohui WangEmail author
  • Yun Zeng
  • Dimitris Samaras
  • Nikos Paragios
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

Extrinsic factors such as object pose and camera parameters are a main source of shape variability and pose an obstacle to efficiently solving shape matching and inference. Most existing methods address the influence of extrinsic factors by decomposing the transformation of the source shape (model) into two parts: one corresponding to the extrinsic factors and the other accounting for intra-class variability and noise, which are solved in a successive or alternating manner. In this chapter, we consider a methodology to circumvent the influence of extrinsic factors by exploiting shape properties that are invariant to them. Based on higher-order graph-based models, we implement such a methodology to address various important vision problems, such as non-rigid 3D surface matching and knowledge-based 3D segmentation, in a one-shot optimization scheme. Experimental results demonstrate the superior performance and potential of this type of approach.

Keywords

Extrinsic Factor Markov Random Field Iterative Close Point Shape Match Markov Random Field Model 
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.

References

  1. 1.
    Ashburner J (2007) A fast diffeomorphic image registration algorithm. NeuroImage 38(1):95–113 CrossRefGoogle Scholar
  2. 2.
    Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522 CrossRefGoogle Scholar
  3. 3.
    Berg AC, Berg TL, Malik J (2005) Shape matching and object recognition using low distortion correspondences. In: CVPR Google Scholar
  4. 4.
    Bertsekas DP (1999) Nonlinear programming, 2nd edn. Athena Scientific, Nashua zbMATHGoogle Scholar
  5. 5.
    Besl PJ, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239–256 CrossRefGoogle Scholar
  6. 6.
    Bishop CM (2006) Pattern recognition and machine learning. Information science and statistics. Springer, Berlin zbMATHGoogle Scholar
  7. 7.
    Blanz V, Vetter T (1999) A morphable model for the synthesis of 3D faces. In: SIGGRAPH Google Scholar
  8. 8.
    Bookstein FL (1989) Principal Warps:Thin-plate splines and the decomposition of deformations. IEEE Trans Pattern Anal Mach Intell 11(6):567–585 zbMATHCrossRefGoogle Scholar
  9. 9.
    Boros E, Hammer PL, Sun X (1991) Network flows and minimization of quadratic pseudo-Boolean functions. Technical report, RRR 17-1991, RUTCOR research report Google Scholar
  10. 10.
    Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell 23(11):1222–1239 CrossRefGoogle Scholar
  11. 11.
    Breiman L (2001) Random forests. Mach Learn 54(2):5–32 MathSciNetCrossRefGoogle Scholar
  12. 12.
    Bronstein AM, Bronstein MM, Kimmel R (2006) Generalized multidimensional scaling: a framework for isometry-invariant partial surface matching. Proc Natl Acad Sci USA 103(5):1168–1172 MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    Bronstein AM, Bronstein MM, Kimmel R, Mahmoudi M, Sapiro G (2010) A Gromov-Hausdorff framework with diffusion geometry for topologically-robust non-rigid shape. Int J Comput Vis 89(2–3):266–286 CrossRefGoogle Scholar
  14. 14.
    do Carmo MP (1976) Differential geometry of curves and surfaces. Prentice Hall, New York zbMATHGoogle Scholar
  15. 15.
    Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681–685 CrossRefGoogle Scholar
  16. 16.
    Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models-their training and application. Comput Vis Image Underst 61(1):38–59 CrossRefGoogle Scholar
  17. 17.
    Duchenne O, Bach F, Kweon I, Ponce J (2009) A tensor-based algorithm for high-order graph matching. In: CVPR Google Scholar
  18. 18.
    Essafi S, Langs G, Deux JF, Rahmouni A, Bassez G, Paragios N (2009) Wavelet-driven knowledge-based MRI calf muscle segmentation. In: ISBI Google Scholar
  19. 19.
    Farkas HM, Kra I (2004) Riemann surfaces. Springer, Berlin Google Scholar
  20. 20.
    Glocker B, Komodakis N, Tziritas G, Navab N, Paragios N (2008) Dense image registration through MRFs and efficient linear programming. Med Image Anal 12(6):731–741 CrossRefGoogle Scholar
  21. 21.
    Gu L, Kanade T (2006) 3D alignment of face in a single image. In: CVPR Google Scholar
  22. 22.
    Heimann T, Meinzer HP (2009) Statistical shape models for 3D medical image segmentation: a review. Med Image Anal 13(4):543–563 CrossRefGoogle Scholar
  23. 23.
    Ishikawa H (2009) Higher-order clique reduction in binary graph cut. In: CVPR Google Scholar
  24. 24.
    Kohli P, Pawan Kumar M, Torr PHS (2009) P3 & beyond: move making algorithms for solving higher order functions. IEEE Trans Pattern Anal Mach Intell 31(9):1645–1656 CrossRefGoogle Scholar
  25. 25.
    Kolmogorov V (2006) Convergent tree-reweighted message passing for energy minimization. IEEE Trans Pattern Anal Mach Intell 28(10):1568–1583 CrossRefGoogle Scholar
  26. 26.
    Kolmogorov V, Rother C (2007) Minimizing nonsubmodular functions with graph cuts—a review. IEEE Trans Pattern Anal Mach Intell 29(7):1274–1279 CrossRefGoogle Scholar
  27. 27.
    Komodakis N, Paragios N, Tziritas G (2011) MRF energy minimization and beyond via dual decomposition. IEEE Trans Pattern Anal Mach Intell 33(3):531–552 CrossRefGoogle Scholar
  28. 28.
    Leordeanu M, Hebert M (2005) A spectral technique for correspondence problems using pairwise constraints. In: ICCV Google Scholar
  29. 29.
    Lin L, Liu X, Zhu SC (2010) Layered graph matching with composite cluster sampling. IEEE Trans Pattern Anal Mach Intell 32(8):1426–1442 CrossRefGoogle Scholar
  30. 30.
    Lipman Y, Funkhouser T (2009) Möbius voting for surface correspondence. ACM Trans Graph 28(3):72:1–72:12 CrossRefGoogle Scholar
  31. 31.
    Qiu H, Hancock ER (2007) Clustering and embedding using commute times. IEEE Trans Pattern Anal Mach Intell 29(11):1873–1890 CrossRefGoogle Scholar
  32. 32.
    Rusinkiewicz S, Levoy M (2001) Efficient variants of the ICP algorithm. In: International conference on 3-d digital imaging and modeling Google Scholar
  33. 33.
    Rustamov RM (2007) Laplace-Beltrami eigenfunctions for deformation invariant shape representation. In: SGP, pp 225–233 Google Scholar
  34. 34.
    Seghers D, Loeckx D, Maes F, Vandermeulen D, Suetens P (2007) Minimal shape and intensity cost path segmentation. IEEE Trans Med Imag 26(8):1115–1129 CrossRefGoogle Scholar
  35. 35.
    Sun J, Ovsjanikov M, Guibas LJ (2009) A concise and provably informative multi-scale signature. based on heat diffusion. Comput Graph Forum 28:1383–1392 CrossRefGoogle Scholar
  36. 36.
    Sundaramoorthi G, Petersen P, Varadarajan VS, Soatto S (2009) On the set of images modulo viewpoint and contrast changes. In: CVPR Google Scholar
  37. 37.
    Torr PHS (2003) Solving Markov random fields using semi definite programming. In: International workshop on artificial intelligence and statistics Google Scholar
  38. 38.
    Torresani L, Kolmogorov V, Rother C (2008) Feature correspondence via graph matching: models and global optimization. In: ECCV Google Scholar
  39. 39.
    Wang C, Teboul O, Michel F, Essafi S, Paragios N (2010) 3D knowledge-based segmentation using pose-invariant higher-order graphs. In: MICCAI Google Scholar
  40. 40.
    Wang C, Zeng Y, Simon L, Kakadiaris I, Samaras D, Paragios N (2011) Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors. In: ICCV Google Scholar
  41. 41.
    Xiang B, Wang C, Deux JF, Rahmouni A, Paragios N (2012) 3D cardiac segmentation with pose-invariant higher-order MRFs. In: ISBI Google Scholar
  42. 42.
    Zeng Y, Wang C, Wang Y, Gu X, Samaras D, Paragios N (2010) Dense non-rigid surface registration using high-order graph matching. In: CVPR Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Chaohui Wang
    • 1
    Email author
  • Yun Zeng
    • 2
  • Dimitris Samaras
    • 2
  • Nikos Paragios
    • 3
    • 4
    • 5
  1. 1.Vision LabUniversity of CaliforniaLos AngelesUSA
  2. 2.Dept. of Computer ScienceStony Brook UniversityStony BrookUSA
  3. 3.Center for Visual ComputingEcole Centrale ParisChâtenay-Malabry CedexFrance
  4. 4.LIGM LaboratoryUniversity Paris-East & Ecole des Ponts Paris-TechMarne-la-ValléeFrance
  5. 5.GALEN GroupINRIA Saclay - Île-de-FranceRocquencourtFrance

Personalised recommendations