Maximally Stable Local Description for Scale Selection

  • Gyuri Dorkó
  • Cordelia Schmid
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3954)


Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve stable local descriptors, and therefore, an improved image representation. The technique performs scale selection based on a region descriptor, here SIFT, and chooses regions for which this descriptor is maximally stable. Maximal stability is obtained, when the difference between descriptors extracted for consecutive scales reaches a minimum. This scale selection technique is applied to multi-scale Harris and Laplacian points. Affine invariance is achieved by an integrated affine adaptation process based on the second moment matrix. An experimental evaluation compares our detectors to Harris-Laplace and the Laplacian in the context of image matching as well as of category and texture classification. The comparison shows the improved performance of our detector.


Scale Invariant Feature Transform Image Match Rotation Invariance Correct Match Moment Matrix 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, Madison, Wisconsin, USA, vol. II, pp. 264–271 (2003)Google Scholar
  2. 2.
    Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 71–84. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or how do I organize my holiday snaps? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 414–431. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Lazebnik, S., Schmid, C., Ponce, J.: Sparse texture representation using affine-invariant neighborhoods. In: CVPR, Madison, Wisconsin, USA, vol. 2, pp. 319–324 (2003)Google Scholar
  5. 5.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  6. 6.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: CVPR, Madison, Wisconsin, USA, vol. 2, pp. 257–263 (2003)Google Scholar
  7. 7.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60(1), 63–86 (2004)CrossRefGoogle Scholar
  8. 8.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  9. 9.
    Lindeberg, T., Garding, J.: Shape-adapted smoothing in estimation of 3D depth cues from affine distortions of local 2D brightness structure. In: ECCV, Stockholm, Sweden, pp. 389–400 (1994)Google Scholar
  10. 10.
    Kadir, T., Zisserman, A., Brady, M.: An affine invariant salient region detector. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 228–241. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  11. 11.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. IJCV 65(1/2), 43–72 (2005)CrossRefGoogle Scholar
  12. 12.
    Tuytelaars, T., Van Gool, L.: Matching widely separated views based on affine invariant regions. IJCV 59(1), 61–85 (2004)CrossRefGoogle Scholar
  13. 13.
    Jurie, F., Schmid, C.: Scale-invariant shape features for recognition of object categories. In: CVPR, Washington, DC, USA, vol. II, pp. 90–96 (2004)Google Scholar
  14. 14.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC, Cardiff, England, pp. 384–393 (2002)Google Scholar
  15. 15.
    Blostein, D., Ahuja, N.: A multi-scale region detector. Computer Vision, Graphics and Image Processing 45(1), 22–41 (1989)CrossRefGoogle Scholar
  16. 16.
    Lindeberg, T.: Feature detection with automatic scale selection. International Journal of Computer Vision 30(2), 79–116 (1998)CrossRefGoogle Scholar
  17. 17.
    Baumberg, A.: Reliable feature matching across widely separated views. In: CVPR, Hilton Head Island, South Carolina, USA, vol. I, pp. 774–781 (2000)Google Scholar
  18. 18.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, pp. 1–22 (2004)Google Scholar
  19. 19.
    Brodatz, P.: Textures: A Photographic Album for Artists and Designers. Dover Publications, New York (1966)Google Scholar
  20. 20.
    Hayman, E., Caputo, B., Fritz, M., Eklundh, J.-O.: On the significance of real-world conditions for material classification. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 253–266. Springer, Heidelberg (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gyuri Dorkó
    • 1
  • Cordelia Schmid
    • 1
  1. 1.INRIA Rhône-AlpesMontbonnotFrance

Personalised recommendations