Abstract
This paper presents a new method for recognizing 3D objects based on the comparison of invariants of their 2D projection curves. We show that Euclidean equivalent 3D surfaces imply affine equivalent 2D projection curves that are obtained from the projection of cross-section curves of the surfaces onto the coordinate planes. Planes used to extract cross-section curves are chosen to be orthogonal to the principal axes of the defining surfaces. Projection curves are represented using implicit polynomial equations. Affine algebraic and geometric invariants of projection curves are constructed and compared under a variety of distance measures. Results are verified by several experiments with objects from different classes and within the same class.
Similar content being viewed by others
References
Costa MS, Shapiro LG (2000) 3D object recognition and pose with relational indexing. Comput Vis Image Underst 79(3):364–407
Forsyth DA, Ponce J (2003) Computer vision: a modern approach. Prentice Hall
Gonzalez E, Adan A, Feliu V, Sanchez L (2008) Active object recognition based on Fourier descriptors clustering. Pattern Recognit Lett 29(8):1060–1071
Kim S, Kweon IS (2008) Scalable representation for 3D object recognition using feature sharing and view clustering. Pattern Recognit 41(2):754–773
Rothganger F, Lazebnik S, Schmid C, Ponce J (2006) 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int J Comput Vis 66(3):231–259
Lee TK, Drew MS (2007) 3D object recognition by eigen-scale-space of contours. In: First international conference on scale space methods and variational methods in computer vision (SSVM’07), pp 883–894
Li W, Bebis G, Bourbakis N (2004) Integrating algebraic functions of views with indexing and learning for 3D object recognition. In: Computer vision and pattern recognition workshop, p 102, June 2004
Nagabhushan P, Guru DS, Shekar BH (2006) Visual learning and recognition of 3D objects using two-dimensional principal component analysis: a robust and an efficient approach. Pattern Recognit 39(4):721–725
Chen H, Bhanu B (2007) 3D free-form object recognition in range images using local surface patches. Pattern Recognit Lett 28(10):1252–1262
Mian AS, Bennamoun M, Owens R (2006) Three-dimensional model-based object recognition and segmentation in cluttered scenes. IEEE Trans Pattern Anal Mach Intell 28(10):1584–1601
Diplaros A, Gevers T, Patras I (2006) Combining color and shape Information for illumination-viewpoint invariant object recognition. IEEE Trans Image Process 15(1):1–11
Shotton J, Blake A, Cipolla R (2008) Multiscale categorical object recognition using contour fragments. IEEE Trans Pattern Anal Mach Intell 30(7):1270–1281
Adan A, Adan M (2004) A flexible similarity measure for 3D shapes recognition. IEEE Trans Pattern Anal Mach Intell 26(11):1507–1520
Shan Y, Sawhney HS, Matei B, Kumar R (2006) Shapeme histogram projection and matching for partial object recognition. IEEE Trans Pattern Anal Mach Intell 28(4):568–577
Pechuk M, Soldea O, Rivlin E (2008) Learning function based classification from 3D imagery. Comput Vis Image Underst 110(2):173–191
Froimovich G, Rivlin E, Shimshoni I, Soldea O (2007) Efficient search and verification for function based classification from real range images. Comput Vis Image Underst 105(3):200–217
Taubin G, Cooper DB (1992) 2D and 3D object recognition and positioning with algebraic invariants and covariants. In: Chapter 6 of Symbolic and numerical computation for artificial intelligence. Academic Press
Huang ZH, Cohen FS (1996) Affine invariant B-spline moments for curve matching. Image Process 5(10):1473–1480
Solina F, Bajcsy R (1990) Recovery of parametric models from range images: The case for superquadrics with global deformations. IEEE Trans Pattern Anal Mach Intell 12(2):131–147
Ma S (1993) Conics-based stereo, motion estimation and pose determination. IJCV 10(1):7–25
Mundy JL, Zisserman A (1992) Geometric invariance in computer vision. The MIT Press
Calabi E, Olver PJ, Shakiban C, Tannenbaum A, Haker S (1998) Differential and numerically invariant signature curves applied to object recognition. IJCV 26(2):107–135
Wu MF, Sheu HT (1998) Representation of 3D surfaces by two-variable Fourier descriptors. IEEE Trans Pattern Anal Mach Intell 20(8):583–588
Taubin G, Cukierman F, Sullivan S, Ponce J, Kriegman DJ (1994) Parameterized families of polynomials for bounded algebraic curve and surface fitting. IEEE PAMI 16:287–303
Keren D, Cooper DB, Subrahmonia J (1994) Describing complicated objects by implicit polynomials. IEEE Trans Pattern Anal Mach Intell 16:38–53
Sahin T, Unel M (2005) Fitting globally stabilized algebraic surfaces to range data. In: 10th IEEE international conference on computer vision (ICCV’05), October 2005
Sahin T, Unel M (2008) Stable algebraic surfaces for 3D object representation. J Math Imaging Vis 32(2):127–137
Sahin T, Unel M (2004) Globally stabilized 3L curve fitting. In: Lecture notes in computer science (LNCS-3211), pp 495–502. Springer
Wolovich W, Unel M (1998) The determination of implicit polynomial canonical curves. IEEE Trans Pattern Analysis Mach Intell 20(10):1080–1089
Unel M, Wolovich WA (1999) A new representation for quartic curves and complete sets of geometric invariants. Int J Pattern Recognit Artif Intell 13(8):1137–1149
Unel M, Wolovich WA (2000) On the construction of complete sets of geometric invariants for algebraic curves. Adv Appl Math 24(1):65–87
Subrahmonia J, Cooper DB, Keren D (1996) Practical reliable bayesian recognition of 2D and 3D objects using implicit polynomials and algebraic invariants. IEEE Trans Pattern Anal Mach Intell 18(5):505–519
Vijayakumar B, Kriegman DJ, Ponce J (1995) Invariant-based recognition of complex curved 3D objects from image contours. In: International conference on computer vision, Boston, MA
Wolovich W, Albakri H, Yalcin H (2002) The precise modeling and measurement of free-form surfaces. J Manuf Sci Eng 2002
Keren D (1994) Using symbolic computation to find algebraic invariants. IEEE Trans Pattern Anal Mach Intell 16(11): 1143–1149
Strang G (1998) Introduction to linear algebra. Wellesley-Cambridge Press
Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley
Sheynin SA, Tuzikov AV (2003) Moment computation for objects with spline curve boundary. IEEE Trans Pattern Anal Mach Intell 25(10): 1317–1322
Faber P, Fischer RB (2001) Pros and cons of Euclidean fitting. In: Proceedings of annual German symposium for pattern recognition (DAGM01, Munich). Springer LNCS 2191, Berlin, pp 414–420, Sep 2001
Blane M, Lei Z et al (2000) The 3L algorithm for fitting implicit polynomial curves and surfaces to data. IEEE Trans Pattern Anal Mach Intell 22(3):298–313
Shilane P, Min P, Kazhdan M, Funkhouser T (2004) The Princeton Shape Benchmark, Shape Modeling International, Genova, Italy, June 2004
Zhang J, Siddiqi K, Macrini D, Shokoufandeh A, Dickinson S (2005) Retrieving articulated 3-D models using medial surfaces and their graph spectra. In: International workshop On energy minimization methods in computer vision and pattern recognition
Stroustrup B (2000) The C++ programming language, special edn. Addison Wesley, Reading, Mass
Numerical Recipes (2007) The art of scientific computing, 3rd edn. Cambridge University Press, ISBN-10: 0521880688
Kitware Inc (2009) The visualization toolkit. http://www.vtk.org/
Viewer M (2009) http://mview.sourceforge.net/
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Unel, M., Soldea, O., Ozgur, E. et al. 3D object recognition using invariants of 2D projection curves. Pattern Anal Applic 13, 451–468 (2010). https://doi.org/10.1007/s10044-010-0179-5
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-010-0179-5