Multimedia Tools and Applications

, Volume 58, Issue 1, pp 81–108 | Cite as

Improving 3D similarity search by enhancing and combining 3D descriptors

  • Benjamin Bustos
  • Tobias Schreck
  • Michael Walter
  • Juan Manuel Barrios
  • Matthias Schaefer
  • Daniel Keim


Effective content-based retrieval in 3D model databases is an important problem that has attracted much research attention over the last years. Many individual methods proposed to date rely on calculating global 3D model descriptors based on image, surface, volumetric, or structural model properties. Descriptors such as these are then input for determining the degree of similarity between models. Traditionally, the ability of individual descriptors to perform effective 3D search is decided by benchmarking. However, in practice the data set on which 3D retrieval is to be applied may differ from the characteristics of the respective benchmark. Therefore, statically determining the descriptor to use based on a fixed benchmark may lead to suboptimal results. We propose a generic strategy to improve the retrieval effectiveness in 3D retrieval systems consisting of multiple model descriptors. The specific contribution of this paper is two-fold. First, we propose to adaptively combine multiple descriptors by forming weighted descriptor combinations, where the weight of each descriptor is decided at query time. Second, we enhance the set of global model descriptors to be combined by including partial descriptors of the same kind in the combinations. Partial descriptors are obtained by applying a given descriptor extractor on the set of parts of a model, obtained by a simple model partitioning scheme. Thereby, more model information is exposed to the 3D descriptors, leading to a more complete object description. We give a systematic discussion of the descriptor combination space involving static and query-adaptive weighting schemes, and based on descriptors of different type and focus (model global vs. partial). The combination of both global and partial model descriptors is shown to deliver improved retrieval precision, compared to policies using single descriptors or fixed-weight combinations. The resulting scheme is generic and can accommodate a large class of global 3D model descriptors.


3D similarity retrieval Descriptor combinations Object partitioning 



We thank Dejan Vranić and Dietmar Saupe for providing the base 3D descriptor extractors used in our work. This work was partially funded by the German Research Foundation DFG within the 2010 German-Chile research cooperation program, project number SCHR 1229/2-1.


  1. 1.
    Akgül CB, Sankur B, Yemez Y, Schmitt F (2008) Similarity score fusion by ranking risk minimization for 3D object retrieval. In: Proc. Eurographics workshop on 3D object retrieval (3DOR’08). Eurographics Association, Aire-la-Ville, pp 41–48Google Scholar
  2. 2.
    Baeza-Yates R, Ribeiro-Neto B (1999) Modern information retrieval. Addison-Wesley, ReadingGoogle Scholar
  3. 3.
    Bronstein A, Bronstein M, Bustos B, Castellani U, Crisani M, Falcidieno B, Guibas L, Kokkinos I, Murino V, Sipiran I, Ovsjanikovy M, Patane G, Spagnuolo M, Sun J (2010) Shrec 2010: robust feature detection and description benchmark. In: Proc. Eurographics workshop on 3D object retrieval (3DOR’10). Eurographics Association, Aire-la-Ville, pp 79–86Google Scholar
  4. 4.
    Bustos B (2006) Index structures for similarity search in multimedia databases. PhD thesis, Department of Computer and Information Science, University of KonstanzGoogle Scholar
  5. 5.
    Bustos B, Skopal T (2006) Dynamic similarity search in multi-metric spaces. In: Proc. 8th ACM SIGMM international workshop on multimedia information retrieval (MIR’06). ACM Press, New York, pp 137–146Google Scholar
  6. 6.
    Bustos B, Keim D, Saupe D, Schreck T, Vranić D (2004a) Automatic selection and combination of descriptors for effective 3D similarity search. In: Proc. IEEE 6th international symposium on multimedia software engineering (ISMSE’04). IEEE Computer Society, New York, pp 514–521CrossRefGoogle Scholar
  7. 7.
    Bustos B, Keim D, Saupe D, Schreck T, Vranić D (2004b) Using entropy impurity for improved 3D object similarity search. In: Proc. IEEE international conference on multimedia and expo (ICME’04). IEEE, New York, pp 1303–1306Google Scholar
  8. 8.
    Bustos B, Keim D, Saupe D, Schreck T, Vranić D (2005a) Feature-based similarity search in 3D object databases. ACM Comput Surv 37(4):345–387CrossRefGoogle Scholar
  9. 9.
    Bustos B, Keim D, Schreck T (2005b) A pivot-based index structure for combination of feature vectors. In: Proc. 20th annual ACM symposium on applied computing, multimedia and visualization track (SAC-MV’05). ACM Press, New York, pp 1180–1184Google Scholar
  10. 10.
    Bustos B, Keim D, Saupe D, Schreck T, Vranić D (2006) An experimental effectiveness comparison of methods for 3D similarity search. Int J Digit Libr (Special issue on multimedia contents and management in digital libraries) 6(1):39–54Google Scholar
  11. 11.
    Bustos B, Keim D, Saupe D, Schreck T (2007) Content-based 3D object retrieval. IEEE Comput Graph Appl (Special issue on 3D documents) 27(4):22–27Google Scholar
  12. 12.
    Castellani U, Cristani M, Fantoni S, Murino V (2008) Sparse points matching by combining 3D mesh saliency with statistical descriptors. Comput Graph Forum 27(2):643–652CrossRefGoogle Scholar
  13. 13.
    Chen J, Ma R, Su Z (2010) Weighting visual features with pseudo relevance feedback for CBIR. In: Proc. 9th ACM international conference on image and video retrieval (CIVR’10). ACM, New York, pp 220–227CrossRefGoogle Scholar
  14. 14.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: CVPR ’05: Proceedings of the 2005 IEEE Computer Society conference on computer vision and pattern recognition (CVPR’05), vol 1. IEEE Computer Society, Washington, DC, pp 886–893. doi: 10.1109/CVPR.2005.177 Google Scholar
  15. 15.
    Duda R, Hart P, Stork D (2001) Pattern classification, 2nd edn. Wiley-Interscience, New YorkMATHGoogle Scholar
  16. 16.
    Frakes W, Baeza-Yates RA (1992) Information retrieval: data structures & algorithms. Prentice-Hall, Englewood CliffsGoogle Scholar
  17. 17.
    Gal R, Cohen-Or D (2006) Salient geometric features for partial shape matching and similarity. ACM Trans Graph 25(1):130–150CrossRefGoogle Scholar
  18. 18.
    Hilaga M, Shinagawa Y, Kohmura T, Kunii T (2001) Topology matching for fully automatic similarity estimation of 3D shapes. In: Proc. ACM international conference on computer graphics and interactive techniques (SIGGRAPH’01). ACM Press, New York, pp 203–212Google Scholar
  19. 19.
    Iyer N, Jayanti S, Lou K, Kalyanaraman Y, Ramani K (2005) Three-dimensional shape searching: state-of-the-art review and future trends. Comput Aided Design 37:509–530CrossRefGoogle Scholar
  20. 20.
    Jayanti S, Kalyanaraman Y, Iyer N, Ramani K (2006) Developing an engineering shape benchmark for cad models. Comput Aided Design 38(9):939–953CrossRefGoogle Scholar
  21. 21.
    Johnson A, Hebert M (1999) Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans Pattern Anal Mach Intell 21(5):433–449CrossRefGoogle Scholar
  22. 22.
    Leng B, Qin Z (2008) A powerful relevance feedback mechanism for content-based 3d model retrieval. Multimed Tools Appl 40(1):135–150CrossRefGoogle Scholar
  23. 23.
    Lou K, Prabhakar S, Ramani K (2004) Content-based three-dimensional engineering shape search. In: Proc. international conference on data engineering (ICDE’04). IEEE Computer Society, New York, pp 754–765CrossRefGoogle Scholar
  24. 24.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  25. 25.
    Mademlis A, Daras P, Tzovaras D, Strintzis MG (2007) On 3D partial matching of meaningful parts. In: Proc. IEEE international conference on image processing (ICIP’07), vol 2. IEEE, New York, pp 517–520Google Scholar
  26. 26.
    Marini S, Spagnuolo M, Falcidieno B (2007) Structural shape prototypes for the automatic classification of 3D objects. Comput Graphi Appl 27(4):28–37CrossRefGoogle Scholar
  27. 27.
    Osada R, Funkhouser T, Chazelle B, Dobkin D (2002) Shape distributions. ACM Trans Graph 21(4):807–832CrossRefGoogle Scholar
  28. 28.
    Papadakis P, Pratikakis I, Theoharis T, Passalis G, Perantonis S (2008) 3D object retrieval using an efficient and compact hybrid shape descriptor. In: Proc. Eurographics workshop on 3D object retrieval (3DOR’08). Eurographics Association, Aire-la-Ville, pp 9–16Google Scholar
  29. 29.
    Rahmani R, Goldman SA, Zhang H, Cholleti SR, Fritts JE (2008) Localized content-based image retrieval. IEEE Trans Pattern Anal Mach Intell 30:1902–1912CrossRefGoogle Scholar
  30. 30.
    Ruggeri M, Saupe D (2008) Isometry-invariant matching of point set surfaces. In: Proc. Eurographics workshop on 3D object retrieval (3DOR’08). Eurographics Association, Aire-la-Ville, pp 17–24Google Scholar
  31. 31.
    Samet H (2005) Foundations of multidimensional and metric data structures (The Morgan Kaufmann series in computer graphics and geometric modeling). Morgan Kaufmann, San FranciscoGoogle Scholar
  32. 32.
    Shilane P, Min P, Kazhdan M, Funkhouser T (2004) The Princeton shape benchmark. In: Proc. international conference on shape modeling and applications (SMI’04). IEEE Computer Society, New York, pp 167–178Google Scholar
  33. 33.
    Sijbers J, Verhoye M, Scheunders P, der Linden AV, Dyck DV, Raman E (1997) Watershed based segmentation of 3D MR data for volume quantization. Magn Reson Imaging 15(6):679–688CrossRefGoogle Scholar
  34. 34.
    Tangelder JWH, Veltkamp RC (2008) A survey of content based 3D shape retrieval methods. Multimed Tools Appl 39(3):441–471CrossRefGoogle Scholar
  35. 35.
    Vranic D (2004) 3D model retrieval. PhD thesis, University of Leipzig, GermanyGoogle Scholar
  36. 36.
    Vranic D (2005) DESIRE: a composite 3D-shape descriptor. In: Proc. IEEE international conference on multimedia and expo (ICME’05). IEEE, Los Alamitos, pp 962–965CrossRefGoogle Scholar
  37. 37.
    Wessel R, Klein R (2010) Learning the compositional structure of man-made objects for 3d shape retrieval. In: Proc. Eurographics workshop on 3D object retrieval (3DOR’10). Eurographics Association, Aire-la-Ville, pp 39–46Google Scholar
  38. 38.
    Wessel R, Novotni M, Klein R (2006) Correspondences between salient points on 3D shapes. In: Proc. GI workshop on vision, modeling, and visualization (VMV’06), pp 365–372Google Scholar
  39. 39.
    Zezula P, Amato G, Dohnal V, Batko M (2005) Similarity search: the metric space approach (Advances in database systems). Springer, SecaucusGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Benjamin Bustos
    • 1
  • Tobias Schreck
    • 2
  • Michael Walter
    • 2
  • Juan Manuel Barrios
    • 1
  • Matthias Schaefer
    • 3
  • Daniel Keim
    • 3
  1. 1.Department of Computer ScienceUniversity of ChileSantiagoChile
  2. 2.Department of Computer ScienceTechnische Universitaet DarmstadtDarmstadtGermany
  3. 3.Department of Computer ScienceUniversity of KonstanzKonstanzGermany

Personalised recommendations