Critical Nets and Beta-Stable Features for Image Matching

  • Steve Gu
  • Ying Zheng
  • Carlo Tomasi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6313)


We propose new ideas and efficient algorithms towards bridging the gap between bag-of-features and constellation descriptors for image matching. Specifically, we show how to compute connections between local image features in the form of a critical net whose construction is repeatable across changes of viewing conditions or scene configuration. Arcs of the net provide a more reliable frame of reference than individual features do for the purpose of invariance. In addition, regions associated with either small stars or loops in the critical net can be used as parts for recognition or retrieval, and subgraphs of the critical net that are matched across images exhibit common structures shared by different images. We also introduce the notion of beta-stable features, a variation on the notion of feature lifetime from the literature of scale space. Our experiments show that arc-based SIFT-like descriptors of beta-stable features are more repeatable and more accurate than competing descriptors. We also provide anecdotal evidence of the usefulness of image parts and of the structures that are found to be common across images.


Image Pair Common Structure Image Match Convex Region Image Part 
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.


  1. 1.
    Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: A survey. Foundations and Trends in Computer Graphics and Vision 3, 177–280 (2008)CrossRefGoogle Scholar
  2. 2.
    Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Transactions on Computers 22, 67–92 (1973)CrossRefGoogle Scholar
  3. 3.
    Manjunath, B.S., Chellappa, R., Von der Malsburg, C.: A feature based approach to face recognition. In: CVPR, pp. 373–378 (1992)Google Scholar
  4. 4.
    Burl, M., Weber, M., Perona, P.: A probabilistic approach to object recognition using local photometry and global geometry. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 628–641. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  5. 5.
    Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: ICCV, vol. 2, pp. 1470–1477 (2003)Google Scholar
  6. 6.
    Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: ECCV Int’l W. on Statistical Learning in Computer Vision (2004)Google Scholar
  7. 7.
    Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: CVPR, vol. 2, pp. 524–531 (2005)Google Scholar
  8. 8.
    Grauman, K., Darrell, T.: The pyramid match kernel: Efficient learning with sets of features. J. of Machine Learning Research 8, 725–760 (2007)Google Scholar
  9. 9.
    Lazebnik, S., Schmid, C., Ponce, J.: Semi-local affine parts for object recognition. In: British Machine Vision C, vol. 2, pp. 959–968 (2004)Google Scholar
  10. 10.
    Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. IJCV 1, 55–79 (2005)Google Scholar
  11. 11.
    Edelsbrunner, H., Harer, J., Zomorodian, A.: Hierarchical Morse complexes for piecewise linear 2-manifolds. In: Symp. on Computational Geometry, pp. 70–79 (2001)Google Scholar
  12. 12.
    Danovaro, E., De Floriani, L., Vitali, M.: Multi-resolution Morse-Smale complexes for terrain modeling. In: Int’l C. on Image Analysis and Processing, pp. 337–342 (2007)Google Scholar
  13. 13.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale-invariant interest points. In: ICCV, pp. 525–531 (2001)Google Scholar
  14. 14.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV, pp. 1150–1157 (1999)Google Scholar
  15. 15.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC (2002)Google Scholar
  16. 16.
    Koenderink, J.J.: The structure of images. Biol. Cybernetics 50, 363–370 (1984)zbMATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Witkin, A., Terzopoulos, D., Kass, M.: Signal matching through scale space. Science, 714–719 (1986)Google Scholar
  18. 18.
    Lindeberg, T.: Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention. IJCV 11, 283–318 (1993)Google Scholar
  19. 19.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30, 77–116 (1998)Google Scholar
  20. 20.
    Florack, L.M.J., Kuijper, A.: The topological structure of scale-space images. J. of Mathematical Imaging and Vision 12, 65–79 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  21. 21.
    Kadir, T., Zisserman, A., Brady, M.: An affine invariant salient region detector. In: ECCV, pp. 228–241 (2004)Google Scholar
  22. 22.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008),
  23. 23.
    Ling, H., Jacobs, D.: Deformation invariant image matching. In: ICCV, vol. 2, pp. 1466–1473 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Steve Gu
    • 1
  • Ying Zheng
    • 1
  • Carlo Tomasi
    • 1
  1. 1.Department of Computer ScienceDuke UniversityDurhamUSA

Personalised recommendations