Multimedia Tools and Applications

, Volume 23, Issue 3, pp 221–235 | Cite as

Robust Object Recognition in Images and the Related Database Problems

  • Laurent Amsaleg
  • Patrick Gros
  • Sid-Ahmed Berrani


Traditional content-based image retrieval systems typically compute a single descriptor per image based for example on color histograms. The result of a query is in general the images from the database whose descriptors are the closest to the descriptor of the query image. Systems built this way are able to return images that are globally similar to the query image, but can not return images that contain some of the objects that are in the query. As opposed to this traditional coarse-grain recognition scheme, recent advances in image processing make fine-grain image recognition possible, notably by computing local descriptors that can detect similar objects in different images. Obviously powerful, fine-grain recognition in images also changes the retrieval process: instead of submitting a single query to retrieve similar images, multiple queries must be submitted and their partial results must be post-processed before delivering the answer. This paper first presents a family of local descriptors supporting fine-grain image recognition. These descriptors enforce robust recognition, despite image rotations and translations, illumination variations, and partial occlusions. Many multi-dimensional indexes have been proposed to speed-up the retrieval process. These indexes, however, have been mostly designed for and evaluated against databases where each image is described by a single descriptor. While this paper does not present any new indexing scheme, it shows that the three most efficient indexing techniques known today are still too slow to be used in practice with local descriptors because of the changes in the retrieval process.

image retrieval systems fine-grain image recognition high dimensional indexing databases 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    L. Amsaleg and P. Gros, “Content-based retrieval using local descriptors: Problems and issues from a database perspective,” Pattern Analysis and Applications, Vol. 4,Nos. 2/3, pp. 108–124, 2001.Google Scholar
  2. 2.
    L. Amsaleg, P. Gros, and S.-A. Berrani, “A robust technique to recognize objects in images, and the DB problems it raises,” in Proc. of the 7th Workshop on Multimedia Information Systems, Capri, Italy, 2001.Google Scholar
  3. 3.
    K. Bennett, U. Fayyad, and D. Geiger, “Density-based indexing for approximate nearest-neighbor queries,” in Proc. of the ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, San Diego, California, USA, 1999, pp. 233–243.Google Scholar
  4. 4.
    S. Berchtold, C. Böm, and H. Kriegel, “The pyramid-technique: Breaking the curse of dimensionality,” in Proc. of the ACM SIGMOD Int. Conf. on Management of Data, Seattle, Washington, USA, 1998, pp. 142–153.Google Scholar
  5. 5.
    S.-A. Berrani, L. Amsaleg, and P. Gros, “Approximate k-nearest-neighbor searches: A new algorithm with probabilistic control of the precision,” Technical Report PI 1495, IRISA, 2002.Google Scholar
  6. 6.
    C. Böhm, S. Berchtold, and D. Keim, “Searching in high-dimensional spaces: Index structures for improving the performance of multimedia databases,” ACM Computing Surveys, Vol. 33,No. 3, 2001.Google Scholar
  7. 7.
    P. Ciaccia and M. Patella, “Pac nearest neighbor queries: Approximate and controlled search in high dimensional and metric spaces,” in Proc. of the Int. Conf. on Data Engineering (ICDE), San Diego, California, USA, 2000, pp. 244–255.Google Scholar
  8. 8.
    Y. Dufournaud, C. Schmid, and R. Horaud, “Matching images with different resolutions,” in Proc. of the Conf. on Computer Vision and Pattern Recognition, Vol. 1, 2000.Google Scholar
  9. 9.
    C. Faloutsos, R. Barber, M. Flickner, J. Hafner, W. Niblack, D. Petkovic, and W. Equitz, “Efficient and effective querying by image content,” Journal of Intelligent Information Systems, Vol. 3, 1994.Google Scholar
  10. 10.
    L. Florack, B. Romeny, J. Koenderink, and M. Viergever, “General intensity transformation and differential invariants,” Journal of Mathematical Imaging and Vision, Vol. 4,No. 2, 1994.Google Scholar
  11. 11.
    A. Guttman, “R-trees: A dynamic index structure for spatial searching,” in Proc. of the ACM SIGMOD Int. Conf. on Management of Data, Boston, Massachusetts, USA, 1984, pp. 47–57.Google Scholar
  12. 12.
    C. Harris and M. Stephens, “A combined corner and edge detector,” in Alvey Vision Conference, 1988.Google Scholar
  13. 13.
    A. Henrich, “The LSDh-tree: An access structure for feature vectors,” in Proc. of the Int. Conf. on Data Engineering (ICDE), Orlando, Florida, USA, 1998, pp. 362–369.Google Scholar
  14. 14.
    A. Hinneburg and D. Keim, “Optimal grid-clustering: Towards breaking the curse of dimensionality in highdimensional clustering,” in Proc. of Int. Conf. on Very Large Databases (VLDB), Edinburgh, Scotland, UK, 1999, pp. 506–517.Google Scholar
  15. 15.
    G. Hjaltason and H. Samet, “Ranking in spatial databases,” in Advances in Spatial Databases, 4th International Symposium, SSD'95, Proceedings, Portland, Maine, USA, 1995, pp. 83–95.Google Scholar
  16. 16.
    C. Li, E. Chang, H. Garcia-Molina, and G. Wiederhold, “Clustering for approximate similarity search in highdimensional spaces,” IEEE Transactions on Knowledge & Data Engineering, Vol. 14,No. 4 pp. 792–808, 2002.Google Scholar
  17. 17.
    N. Roussopoulos, S. Kelley, and F. Vincent, “Nearest neighbor queries,” in Proc. of the ACM SIGMOD Int. Conf. on Management of Data, San Jose, California, USA, 1995, pp. 71–79.Google Scholar
  18. 18.
    C. Schmid and R. Mohr, “Local grayvalue invariants for image retrieval,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19,No. 5, 1997.Google Scholar
  19. 19.
    C. Schmid, R. Mohr, and C. Bauckhage, “Comparing and evaluating interest points,” in Proc. of the 6th Int. Conf. on Computer Vision, IEEE Computer Society Press, 1998.Google Scholar
  20. 20.
    R. Weber and K. Böhm, “Trading quality for time with nearest neighbor search,” in Proc. of the Int. Conf. on Extending Database Technology (EDBT), Konstanz, Germany, 2000, pp. 21–35.Google Scholar
  21. 21.
    R. Weber, H. Schek, and S. Blott, “A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces,” in Proc. of Int. Conf. on Very Large Databases (VLDB), New York City, New York, USA, 1998, pp. 194–205.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Laurent Amsaleg
    • 1
  • Patrick Gros
    • 1
  • Sid-Ahmed Berrani
    • 2
  1. 1.Irisa–CNRS, Campus de BeaulieuRennesFrance
  2. 2.Thomson Multimédia R&D FranceCesson-SévignéFrance

Personalised recommendations