Recognition of 3D objects from 2D images — Some issues

  • B. Liu
  • P. Wang
2D and 3D Shape Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1121)


This paper presents a simple methods for visualizing, understanding, interpreting, and recognizing 3D objects from 2D images. It extended the linear combination methods, uses parallel pattern matching and can handle 3D rigid concave objects as well convex objects and articulated objects, yet, needs only a very small number of learning samples. Some real images are illustrated, with future research discussed.


3D object recognition 2D images realization visualization understanding recognition concave objects convex objects rigid objects linear combination parallel pattern matching articulated objects learning 


  1. 1.
    L. Baird and P. Wang, „3D Object Perception Using Gradient Descent“, Int. Journal of Mathematical Imaging and Vision (IJMIV), 5, 111–117, 1995Google Scholar
  2. 2.
    R. Basri, „Viewer-Centered Representations in Object Recognition: A Computational Approach”, Handbook of Pattern Recognition and Computer Vision, pp. 863–882, WSP (1993)Google Scholar
  3. 3.
    R. Brooks, „Symbolic reasoning around 3-d models and 2-d images“, Arti.Int., 17, 285–348, 1981Google Scholar
  4. 4.
    R. Goldberg and D. Lowe, „Verification of 3-d parametric models in 2-d image data“, Proc. IEEE Workshop on Computer Vision, 255–267, 1987Google Scholar
  5. 5.
    W.E.L. Grimson and T. Lozano-Perez, „Localizing overlapping parts by searching the interpretation tree“, IEEE-PAMI, 9(4), 469–482, 1987Google Scholar
  6. 6.
    T. Marill, „Emulating the human interp. of line-drawings as 3d objects“, IJCV, v6-2, 1991, 147–161Google Scholar
  7. 7.
    P. Wang, „Recognizing 3D Articulated Line-Drawing Objects“, 120/SPIE vol. 2056 Intelligent Robots and Computer Vision XII (1993) pp120–131Google Scholar
  8. 8.
    P. Wang, „3D Line Image Analysis — A Heuristic Parallel Approach with Learning and Recognition“, Info. Sciences v81, 1994 pp. 155–176Google Scholar
  9. 9.
    P. Wang, „A Heuristic Approach for 3D Articulated Line-Drawing Object Pattern Representation and Recognition“, Advances in Imaging Technologies (ed by E.Dougherty), Marcel Dekker, 1994, 197–221Google Scholar
  10. 10.
    P. Winston, Artificial Intelligence, Cha. 26 „Recognizing Objects“, pp. 531–551, Addision Wesley, 1994Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • B. Liu
    • 1
  • P. Wang
    • 1
  1. 1.Northeastern UniversityBoston

Personalised recommendations