The Visual Computer

, Volume 26, Issue 10, pp 1321–1338 | Cite as

3D relevance feedback via multilevel relevance judgements

  • D. Giorgi
  • P. Frosini
  • M. Spagnuolo
  • B. Falcidieno
Original Article

Abstract

Relevance feedback techniques are expected to play an important role in 3D search engines, as they help to bridge the semantic gap between the user and the system. Indeed, similarity is a cognitive process that depends on the observer. We propose a novel relevance feedback technique, which relies on the assumption that similarity may emerge from the inhibition of differences, i.e., from the lack of diversity with respect to the shape properties taken into account. To this end, a user is provided with a variety of shape descriptors, each analyzing different shape properties. Then the user expresses his/her multilevel relevance judgements, which correspond to his/her concept of similarity among the retrieved objects. Finally, the system inhibits the role of the shape properties that do not reflect the user’s idea of similarity. The feedback technique is based on a simple scaling procedure, which does not require neither a priori learning nor parameter optimization. We show examples and experiments on a benchmark dataset of 3D models.

Keywords

3D retrieval 3D similarity User feedback Relevance scale Pseudodistances Approximation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
  3. 3.
  4. 4.
    TOSCA = Toolbox for Surface Comparison and Analysis. Web: http://tosca.cs.technion.ac.il
  5. 5.
    Akgül, C., Sankur, B., Schmitt, F., Yemez, Y.: Density-based shape descriptors for 3D object retrieval. In: Proc. MRCS. LNCS, vol. 4105, pp. 322–329. Springer, Berlin (2006) Google Scholar
  6. 6.
    Akgül, C., Sankur, B., Yemez, Y., Schmitt, F.: Similarity learning for 3D object retrieval using relevance feedback and risk minimization. Int. J. Comput. Vis. 89(23), 392–407 (2010) CrossRefGoogle Scholar
  7. 7.
    Albertoni, R., De Martino, M.: Asymmetric and context-dependent semantic similarity among ontology instances. J. Data Semant. 10, 1–30 (2008) CrossRefGoogle Scholar
  8. 8.
    Atmosukarto, I., Leow, W., Huang, Z.: Feature combination and relevance feedback for 3D model retrieval. In: Proc. 11th Multimedia Modelling Conference, pp. 334–339 (2005) Google Scholar
  9. 9.
    Attene, M., Robbiano, F., Spagnuolo, M., Falcidieno, B.: Characterization of 3D shape parts for semantic annotation. Comput. Aided Design 41(10), 756–763 (2009) CrossRefGoogle Scholar
  10. 10.
    Bang, H., Chen, T.: Feature space warping: an approach to relevance feedback. In: Proc. IEEE Int. Conf. on Image Processing, pp. 22–25 (2002) Google Scholar
  11. 11.
    Biasotti, S., De Floriani, L., Falcidieno, B., Frosini, P., Giorgi, D., Landi, C., Papaleo, L., Spagnuolo, M.: Describing shapes by geometrical-topological properties of real functions. ACM Comput. Surv. 40(4), 12:1–12:87 Google Scholar
  12. 12.
    Biasotti, S., Falcidieno, B., Frosini, P., Giorgi, D., Landi, C., Marini, S., Patané, G., Spagnuolo, M.: 3d shape description and matching based on properties of real functions. In: Eurographics 2007 Tutorial Notes, pp. 1025–1074. The Eurographics Association, Geneve (2007) Google Scholar
  13. 13.
    Biasotti, S., Giorgi, D., Spagnuolo, M., Falcidieno, B.: Size functions for comparing 3D models. Pattern Recognit. 41, 2855–2873 (2008) MATHCrossRefGoogle Scholar
  14. 14.
    Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical Geometry of Nonrigid Shapes. Springer, Berlin (2008) Google Scholar
  15. 15.
    Bronstein, M.M., Bronstein, A.M., Kimmel, R., Yavneh, I.: Multigrid multidimensional scaling. Numer. Linear Algebra Appl. 36(2–3), 149–171 (2006). Special issue on multigrid methods CrossRefMathSciNetGoogle Scholar
  16. 16.
    Bustos, B., Keim, D., Saupe, D., Schrek, T., Vranic, D.: Feature-based similarity search in 3D object databases. ACM CSUR 37(4), 345–387 (2005) CrossRefGoogle Scholar
  17. 17.
    Chaouch, M., Verroust-Blondet, A.: 3D model retrieval based on depth line descriptor. In: Proc. ICME’07. IEEE (2007) Google Scholar
  18. 18.
    Chen, D., Ouhyoung, M., Tian, X., Shen, Y.: On visual similarity based 3D model retrieval. Comput. Graph. Appl. 22, 223–232 (2003) Google Scholar
  19. 19.
    Datta, R., Joshi, D., Li, J., Wang, J.: Image retrieval: ideas, influences and trends of the new age. ACM Comput. Surv. 40(2), 1–60 (2008) CrossRefGoogle Scholar
  20. 20.
    Del Bimbo, A., Pala, P.: Content-based retrieval of 3D models. ACM Trans. Multimedia Comput. Commun. Appl. 2(1), 20–43 (2006) CrossRefGoogle Scholar
  21. 21.
    Elad, A., Kimmel, R.: On bending invariant signatures for surfaces. IEEE Trans. Pattern Anal. Mach. Intell. 25(10), 1285–1295 (2003) CrossRefGoogle Scholar
  22. 22.
    Elad, M., Tal, A., Ar, S.: Content-based retrieval of VRML objects—an iterative and interactive approach. In: Proc. EG Multimedia, pp. 97–108 (2001) Google Scholar
  23. 23.
    Escolano, F., Suau, P., Bonev, B.: Information Theory in Computer Vision and Pattern Recognition. Springer, Berlin (2009) MATHCrossRefGoogle Scholar
  24. 24.
    Falcidieno, B., Spagnuolo, M.: The Role of Ontologies for 3D Media Applications. Springer, London (2007), pp. 185–205 Google Scholar
  25. 25.
    Falcidieno, B., Spagnuolo, M., Alliez, P., Quak, E., Vavalis, E., Houstis, C.: Towards the semantics of digital shapes: the AIM@SHAPE approach. In: Proc. EWIMT2004—European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology, pp. 1–4 (2004) Google Scholar
  26. 26.
    Frosini, P., Landi, C.: Size theory as a topological tool for computer vision. Pattern Recognit. Image Anal. 9, 596–603 (1999) Google Scholar
  27. 27.
    Funkhouser, T., Min, P., Kazhdan, M., Chen, J., Halderman, A., Dobkin, D.: A search engine for 3D models. ACM Trans. Graph. 22(1), 83–105 (2003) CrossRefGoogle Scholar
  28. 28.
    Gandar, B., Loosli, G., Deffuant, G.: How to optimize sample in active learning: Dispersion, an optimum criterion for classification. In: Proc. Conférence europénne ENBIS, (2009) Google Scholar
  29. 29.
    Giorgi, D., Attene, M., Patané, G., Marini, S., Pizzi, C., Biasotti, S., Spagnuolo, M., Falcidieno, B., Corvi, M., Usai, L., Roncarolo, L., Garibotto, G.: A critical assessment of 2D and 3D face recognition algorithms. In: Proc. AVSS 2009: 6th IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, pp. 79–84 (2009) Google Scholar
  30. 30.
    Giorgi, D., Biasotti, S., Paraboschi, L.: Watertight models track. Tech. Rep. IMATI-CNR-GE 09/07 (2007) Google Scholar
  31. 31.
    Giorgi, D., Frosini, P., Spagnuolo, M., Falcidieno, B.: Multilevel relevance feedback for 3D shape retrieval. In: Proc. 3DOR’09: Eurographics Workshop on 3D Object Retrieval, pp. 45–52 (2009) Google Scholar
  32. 32.
    Hu, B., Liu, Y., Gao, S., Hu, J., Sun, R.: A powerful partial relevance feedback for 3D model retrieval. J. Multimedia 4(3), 120–128 (2009) Google Scholar
  33. 33.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3D shape descriptors. In: Proc. SGP 2003: Eurographics Symposium on Geometry Processing, pp. 156–165 (2003) Google Scholar
  34. 34.
    Kherfi, M., Ziou, D., Bernardi, A.: Combining positive and negative examples in relevance feedback for content-based image retrieval. J. Vis. Commun. Image Represent 14(3), 428–547 (2006) Google Scholar
  35. 35.
    Koenderink, J.: Solid Shape. MIT Press, Cambridge (1990) Google Scholar
  36. 36.
    Leifman, G., Meir, R., Tal, A.: Semantic-oriented 3D shape retrieval using relevance feedback. Vis. Comput. 21, 865–875 (2005) CrossRefGoogle Scholar
  37. 37.
    Leng, B., Qin, Z.: A powerful relevance feedback mechanism for content-based 3D model retrieval. Multimed. Tools Appl. 40, 135–150 (2008) CrossRefGoogle Scholar
  38. 38.
    Martínez, J., Koenen, R., Pereira, F.: MPEG-7: the generic multimedia content description standard, part i. IEEE Multimed. 2, 78–87 (2002) CrossRefGoogle Scholar
  39. 39.
    Novotni, M., Park, G.J., Wessel, R., Klein, R.: Evaluation of kernel based methods for relevance feedback in 3D shape retrieval. In: Proc. 4th International Workshop on Content-Based Multimedia Indexing (CBMI’05) (2005) Google Scholar
  40. 40.
    Onasoglou, E., Daras, P.: Semantic force relevance feedback, content free 3D object retrieval and annotation propagation: bridging the gap and beyond. Multimed. Tools Appl. 39, 217–241 (2008) CrossRefGoogle Scholar
  41. 41.
    Papadakis, P., Pratikakis, I., Trafalis, T., Theoharis, T., Perantonis, S.: Relevance feedback in content-based 3D object retrieval: a comparative study. CAD Appl. 5(5), 753–763 (2008) Google Scholar
  42. 42.
    Rocchio, J.: Relevance Feedback in Information Retrieval. Prentice Hall, New York (1971) Google Scholar
  43. 43.
    Rosman, G., Bronstein, M.M., Bronstein, A.M., Kimmel, R.: Topologically constrained isometric embedding. Hum. Motion, Underst. Model. Capture Animat. Comput. Imaging Vis. 36(2), 243–262 (2008) Google Scholar
  44. 44.
    Rui, Y., Wang, T., Ortega, M., Methotra, S.: Relevance feedback: a power tool in interactive content-based image retrieval. IEEE Trans. Circuits Syst. Video Technol. 8(5), 644–655 (1998) CrossRefGoogle Scholar
  45. 45.
    Salton, G.: Introduction to Modern Information Retrieval. McGraw, New York (1983) MATHGoogle Scholar
  46. 46.
    Smeulders, A., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349–1380 (2000) CrossRefGoogle Scholar
  47. 47.
    Tangelder, J., Veltkamp, R.: A survey of content-based 3D shape retrieval methods. Multimed. Tools Appl. 39(3), 441–471 (2008) CrossRefGoogle Scholar
  48. 48.
    Tung, T., Schmitt, F.: The augmented multiresolution Reeb graph approach for content-based retrieval of 3D shapes. IJSM 11(1) (2005) Google Scholar
  49. 49.
    Veltkamp, R., ter Haar, F.: 3D shape retrieval contest. Tech. Rep. UU-CS-2007-015 (2007) Google Scholar
  50. 50.
    Wu, H., Lu, H., Ma, S.: Willhunter: Interactive image retrieval with multilevel relevance measurement. In: Proc. IEEE Int. Conf. on Image Processing, pp. 22–25 (2002) Google Scholar
  51. 51.
    Wu, H., Lu, H., Ma, S.: Multilevel relevance judgement, loss function and performance measure in image retrieval. In: Proc. CIVR. LNCS, vol. 2728. Springer, Berlin (2003) Google Scholar
  52. 52.
    Zarpalas, D., Daras, P., Axenopoulos, A., Tzovaras, D., Strintzis, M.: 3D model search and retrieval using the spherical trace transform. EURASIP J. Adv. Signal Process. (2007). doi: 10.1155/2007/23912 MATHGoogle Scholar
  53. 53.
    Zhou, X., Thomas, S.: Relevance feedback in image retrieval: a comprehensive review. Multimedia Syst. 5(8), 536–544 (2003) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • D. Giorgi
    • 1
  • P. Frosini
    • 2
  • M. Spagnuolo
    • 1
  • B. Falcidieno
    • 1
  1. 1.IMATI-CNRGenovaItaly
  2. 2.ARCES & Dept. of MathematicsUniversity of BolognaBolognaItaly

Personalised recommendations