Multi-view Feature Matching and Image Grouping from Multiple Unordered Wide-Baseline Images

  • Xiuyuan Zeng
  • Heng Yang
  • Qing Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5359)


In this paper, we present a photo grouping method in multi-view feature matching problem, especially from multiple unordered wide-baseline images. By analyzing and comparing the connections between images with undirected weighted graph, we abstract the photo grouping into a nonlinear optimization problem and tackle it by using an annealing based method. Additionally, a new high-dimensional feature searching algorithm is also developed to find out the initial features matching number more robustly, which is used to be the measurement of image relativities in the grouping algorithm. Finally, we show the analyses and discussions of the performance of the proposed method and experimental results have proven that the novel approach is more efficient than the traditional ones.


Feature Vector Image Pair Feature Match Image Grouping Nonlinear Optimization Problem 
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.
    Schaffalitzky, F., Zisserman, A.: Multi-view Matching for Unordered Image Sets, or How Do I Organize My Holiday Snaps?. In: ECCV, vol. 1, pp. 414–431 (2002)Google Scholar
  2. 2.
    Brown, M., Szeliski, R., Winder, S.: Multi-image matching using multi-scale oriented patches. In: CVPR, vol. 1, pp. 510–517 (2005)Google Scholar
  3. 3.
    Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: Exploring photo collections in 3D. ACM Transactions on Graphics (SIGGRAPH Proceedings) 25(3), 835–846 (2006)CrossRefGoogle Scholar
  4. 4.
    Brown, M., Lowe, D.G.: Automatic Panoramic Image Stitching Using Invariant Features. IJCV, 59–73 (2007)Google Scholar
  5. 5.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  6. 6.
    Nene, S.A., Nayar, S.K.: A Simple Algorithm for Nearest Neighbor Search in High Dimensions. IEEE PAMI 9(19), 989–1003 (1997)CrossRefGoogle Scholar
  7. 7.
    Yu, C., Ooi, B.C., Tan, K.L., Jgadish, H.V.: Indexing the Distance: An Efficient Method to KNN Processing. In: Proceedings of the 27th VLDB Conference, pp. 421–430 (2001)Google Scholar
  8. 8.
    Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: ICCV, pp. 1470–1477 (2003)Google Scholar
  9. 9.
    Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: CVPR, pp. 2161–2168 (2006)Google Scholar
  10. 10.
    Yao, J., Cham, W.K.: Robust multi-view feature matching from multiple unordered views. Pattern Recognition 40, 3081–3099 (2007)CrossRefzbMATHGoogle Scholar
  11. 11.
    Ferrari, V., Tuytelaars, T., Van Gool, L.J.: Wide-baseline multiple-view correspondences. In: IEEE Conference on Computer Vision & Pattern Recognition (CVPR 2003), Wisconsin, Madison, USA, June 2003, vol. 1, pp. 718–725 (2003)Google Scholar
  12. 12.
    Ke, Y., Sukthankar, R.: PCA-sift: A more distinctive representation for local image descriptors. In: CVPR, pp. 506–513 (2004)Google Scholar
  13. 13.
  14. 14.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Xiuyuan Zeng
    • 1
  • Heng Yang
    • 1
  • Qing Wang
    • 1
  1. 1.School of Computer Science and EngineeringNorthwestern Polytechnical UniversityXi’anP. R. China

Personalised recommendations