Two Sample Tests for Mean 3D Projective Shapes from Digital Camera Images



In this article, we extend mean 3D projective shape change in matched pairs to independent samples. We provide a brief introduction of projective shapes of spatial configurations obtained from their digital camera images, building on previous results of Crane and Patrangenaru (J Multivar Anal 102:225–237, 2011). The manifold of projective shapes of k-ads in 3D containing a projective frame at five given landmark indices has a natural Lie group structure, which is inherited from the quaternion multiplication. Here, given the small sample size, one estimates the mean 3D projective shape change in two populations, based on independent random samples of possibly different sizes using Efron’s nonparametric bootstrap. This methodology is applied in three relevant applications of analysis of 3D scenes from digital images: visual quality control, face recognition, and scene recognition.


3D scene reconstruction from a pair of uncalibrated camera views 3D projective shape Quaternions Fréchet means Extrinsic mean change on a Lie group Asymptotic statistics on manifolds Nonparametric bootstrap on manifolds Computational statistics Visual quality control Face recognition 

AMS 2000 Subject Classifications

Primary 62H11; Secondary 62H10 62H35 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Beran R, Fisher NI (1998) Nonparametric comparison of mean axes. Ann Stat 26:472–493CrossRefMATHMathSciNetGoogle Scholar
  2. Bhattacharya A (2008) Statistical analysis on manifolds: a nonparametric approach for inference on shape spaces. Sankhya Ser A 70(2):223–266MATHGoogle Scholar
  3. Bhattacharya RN, Bhattacharya A (2012) Nonparametric statistics on manifolds with applications to shape spaces. In: Institute of mathematical statistics lecture notes–monograph series, vol 3. Cambridge University Press.Google Scholar
  4. Bhattacharya RN, Ellingson L, Liu X, Patrangenaru V, Crane M (2012) Extrinsic analysis on manifolds is computationally faster than intrinsic analysis, with applications to quality control by machine vision. Appl Stoch Model Bus Ind 28:222–235CrossRefMathSciNetGoogle Scholar
  5. Bhattacharya RN, Ghosh JK (1978) On the validity of the formal Edgeworth expansion. Ann Stat 6(2):434–451CrossRefMATHMathSciNetGoogle Scholar
  6. Bhattacharya RN, Patrangenaru V (2003) Large sample theory of intrinsic and extrinsic sample means on manifolds—part I. Ann Stat 31(1):1–29CrossRefMATHMathSciNetGoogle Scholar
  7. Bhattacharya RN, Patrangenaru V (2005) Large sample theory of intrinsic and extrinsic sample means on manifolds—part II. Ann Stat 33(3):1211–1245CrossRefMathSciNetGoogle Scholar
  8. Billingsley P (1995) Probability and measure, 3rd edn. Eds WileyGoogle Scholar
  9. Buibas M, Crane M, Ellingson L, Patrangenaru V (2012) A projective frame based shape analysis of a rigid scene from noncalibrated digital camera imaging outputs. In: JSM proceedings, 2011, institute of mathematical statistics. Miami, FL, pp 4730–4744Google Scholar
  10. Crane M, Patrangenaru V (2011) Random change on a Lie group and mean glaucomatous projective shape change detection from stereo pair image. J Multivar Anal 102:225–237CrossRefMATHMathSciNetGoogle Scholar
  11. Efron B (1982) The Jackknife, the Bootstrap and other resampling plans. In: CBMS-NSF regional conference series in applied mathematics, vol 38. SIAMGoogle Scholar
  12. Faugeras OD (1992) What can be seen in three dimensions with an uncalibrated stereo rig? In: Proc. European conference on computer vision, LNCS, vol 588, pp 563–578Google Scholar
  13. Fisher NI, Hall P, Jing B-Y, Wood ATA (1996) Improved pivotal methods for constructing confidence regions with directional data. J Am Stat Assoc 91:1062–1070CrossRefMATHMathSciNetGoogle Scholar
  14. Fréchet M (1948) Les élements aléatoires de nature quelconque dans un espace distancié. Ann Inst H Poincaré 10:215–310Google Scholar
  15. Ma Y, Soatto S, Kosecka J, Sastry SS (2006) An invitation to 3-D vision. Springer, New YorkGoogle Scholar
  16. Goodall C, Mardia KV (1999) Projective shape analysis. J Graph Comput Stat 8:143–168MathSciNetGoogle Scholar
  17. Hall P (1997) The bootstrap and Edgeworth expansion. Springer Series in Statistics, New YorkGoogle Scholar
  18. Hall P, Hart JD (1990) Bootstrap test for difference between means in nonparametric regression. J Am Stat Assoc 85:1039–104CrossRefMATHMathSciNetGoogle Scholar
  19. Hartley RI, Gupta R, Chang T (1992) Stereo from uncalibrated cameras. In: Proc. IEEE conference on computer vision and pattern recognition, pp 761–764Google Scholar
  20. Hartley RI, Zisserman A (2004) Multiple view geometry in computer vision, 2nd edn. Cambridge University PressGoogle Scholar
  21. Hendriks H, Landsman Z (1998) Mean location and sample mean location on manifolds: asymptotics, tests, confidence regions. J Multivar Anal 67(2):227–243CrossRefMATHMathSciNetGoogle Scholar
  22. Johnson RA,Wichern DW (2007) Applied multivariate statistical analysis, 6th edn. Prentice HallGoogle Scholar
  23. Longuet-Higgins C (1981) A computer algorithm for reconstructing a scene from two projections. Nature 293:133–135CrossRefGoogle Scholar
  24. Mardia KV, Goodall C, Walder A (1996) Distributions of projective invariants and model-based machine vision. Adv Appl Probab 28:641–661CrossRefMATHMathSciNetGoogle Scholar
  25. Mardia KV, Patrangenaru V (2005) Directions and projective shapes. Ann Stat 33:1666–1699CrossRefMATHMathSciNetGoogle Scholar
  26. Mardia KV, Patrangenaru V, Derado G, Patrangenaru VP (2003) Reconstruction of planar scenes from multiple views using affine and projective shape. In: Proceedings of the 2003 workshop on statistical signal processing, pp 285–288Google Scholar
  27. Munk A, Paige R, Pang J, Patrangenaru V, Ruymgaart FH (2008) The one and multisample problem for functional data with applications to projective shape analysis. J Multiv Anal 99:815–833CrossRefMATHMathSciNetGoogle Scholar
  28. Osborne D, Patrangenaru V, Ellingson L, Groisser D, Schwartzman A (2013) Nonparametric two-sample tests on homogeneous Riemannian manifolds, Cholesky decompositions and diffusion tensor image analysis. J Multivar Anal 103:163–175CrossRefMathSciNetGoogle Scholar
  29. Patrangenaru V (1999) Moving projective frames and spatial scene identification. In: Mardia KV, Aykroyd RG, Dryden IL (eds) Proceedings in spatial-temporal modeling and applications. Leeds University Press, pp 53–57Google Scholar
  30. Patrangenaru V (2001) New large sample and bootstrap methods on shape spaces in high level analysis of natural images. Commun Stat Theory Methods 30:1675–1695CrossRefMATHMathSciNetGoogle Scholar
  31. Patrangenaru V, Crane MA, Liu X, Descombes X, Derado G, Liu W, Balan V, Patrangenaru VP, Thompson HW (2012) Methodology for 3D scene reconstruction from digital camera images. In: Proceedings of the international conference of Differential Geometry and Dynamical Systems (DGDS-2011), vol 19, BSG Proceedings, 6–9 October 2011. Bucharest, Romania, pp 110–124Google Scholar
  32. Patrangenaru V, Liu X, Sugathadasa S (2010) Nonparametric 3D projective shape estimation from pairs of 2D images—I, in memory of Dayawansa WP. J Multivar Anal 101:11–31CrossRefMATHMathSciNetGoogle Scholar
  33. Spivak M (1979) A comprehensive introduction to differential geometry, vols I–II, 2nd edn. Publish or Perish, Inc., Wilmington, DelGoogle Scholar
  34. Sughatadasa SM (2006) Affine and projective shape analysis with applications. Ph.D. Dissertation, Texas Tech UnivesityGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Department of StatisticsFlorida State UniversityTallahasseeUSA
  2. 2.Brain CorporationSan DiegoUSA

Personalised recommendations