An Interactive Approach to Solving Correspondence Problems

Article

Abstract

Finding correspondences among objects in different images is a critical problem in computer vision. Even good correspondence procedures can fail, however, when faced with deformations, occlusions, and differences in lighting and zoom levels across images. We present a methodology for augmenting correspondence matching algorithms with a means for triaging the focus of attention and effort in assisting the automated matching. For guiding the mix of human and automated initiatives, we introduce a measure of the expected value of resolving correspondence uncertainties. We explore the value of the approach with experiments on benchmark data.

Keywords

Human interaction Active learning Value of information Matching Correspondence problems 

References

  1. Caetano, T., McAuley, J., Cheng, L., Le, Q., & Smola, A. (2009). Learning graph matching. In IEEE Trans. on Pattern Analysis and Machine Intelligence (pp. 2349–2374).Google Scholar
  2. Chegireddy, C. R., & Hamacher, H. W. (1987). Algorithms for finding \(k\)-best perfect matchings. Discrete Applied Mathematics, 18, 155–165.CrossRefMATHMathSciNetGoogle Scholar
  3. Chli, M., & Davison, A. J. (2008). Active matching. In European Conference on Computer Vision (ECCV) 2008, Part I. Lecture Note in Computer Science (Vol. 5302, pp. 72–85). Heidelberg: Springer.Google Scholar
  4. Cho, Y., Lee, J., & Lee, K. M. (2010). Reweighted random walks for graph matching. In European Conference on Computer Vision (ECCV).Google Scholar
  5. Chvatal, V. (1979). A greedy heuristic for the set covering problem. Math of Operations Research, 4(3), 233–235.CrossRefMATHMathSciNetGoogle Scholar
  6. Cour, T., Srinivasan, P., & Shi, J. (2006). Balanced graph matching. In Advances in Neural Information Processing Systems (NIPS).Google Scholar
  7. Dasgupta, S. (2004). Analysis of a greedy active learning strategy. In Advances in Neural Information Processing Systems (NIPS).Google Scholar
  8. Debevec, P., Taylor, C., & Malik, J. (1996). Modeling and rendering architecture from photographs: A hybrid geometry- and image-based approach. In Computer Graphics SIGGRAPH 1996 Proceedings.Google Scholar
  9. Duchenne, O., Bach, F., Kweon, I., & Ponce, J. (2009). A tensor-based algorithm for high-order graph matching. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  10. Escolano, F., Hancock, E., & Lozano, M. (2011). Graph matching through entropic manifold alignment. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  11. Freund, Y., Seung, H. S., Shamir, E., & Tishby, N. (1997). Selective sampling using the query by committee algorithm. Machine Learning, 28(2—-3), 133–168.CrossRefMATHGoogle Scholar
  12. Goodrich, M., & Mitchell, J. (1999). Approximate geometric pattern matching under rigid motions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(4), 371–379.CrossRefGoogle Scholar
  13. Handa, A., Chli, M., Strasdat, H., & Davison, A. J. (2010). Scalable active matching. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  14. Heckerman, D., Horvitz, E., & Nathwani, B. N. (1992). Toward normative expert systems: Part i the pathfinder project. Methods of Information in Medicine, 31, 90–105.Google Scholar
  15. Howard, R. (1967). Value of information lotteries. IEEE Transaction on Systems, Science and, Cybernetics, SSC–3(1), 54–60.CrossRefGoogle Scholar
  16. Joshi, A. J., & Porikli, F. N. P. (2009). Multi-class active learning for image classification. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  17. Kamar, E. , & Horvitz, E. (2013). A Monte-Carlo approach to computing value of information: Procedure and experiments. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS).Google Scholar
  18. Kamar, E., Hacker, S., & Horvitz, E. (2012). Combining human and machine intelligence in large-scale crowdsourcing. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS).Google Scholar
  19. Kapoor, A., Horvitz, E., & Basu, S. (2007). Selective supervision: Guiding supervised learning with decision-theoretic active learning. In International Joint Conference on Artificial Intelligence.Google Scholar
  20. Kapoor, A., Grauman, K., Urtasun, R., & Darrell, T. (2009). Gaussian processes for object categorization. International Journal of Computer Vision, 88(2), 169–188.CrossRefGoogle Scholar
  21. Kowdle, A., Chang, Y., Gallagher, A., & Chen, T. (2011). In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  22. Krause, A., Singh, A., & Guestrin, C. (2008). Near-optimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies. Journal of Machine Learning Research, 9, 235–284.MATHGoogle Scholar
  23. Lawrence, N., Seeger, M., Herbrich, R. (2002). Fast sparse Gaussian process method: Informative vector machines. In Advances in Neural Information Processing Systems (NIPS) (Vol. 15). Cambridge: MIT PressGoogle Scholar
  24. Lee, J., Cho, M., & Lee, K. (2011). Hyper-graph matching via reweighted random walks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  25. Lordeanu, M., & Hebert, M. (2005). A spectral technique for correspondence problems using pairwise constraints. In International Conference on Computer Vision (ICCV).Google Scholar
  26. Lovász, L. (1993). Random walks on graphs: a survey. Combinatorics: Paul Erdös is Eighty, 2, 1–46.Google Scholar
  27. MacKay, D. (1992). Information-based objective functions for active data selection. Neural Computation, 4(4), 589.CrossRefGoogle Scholar
  28. Maji, S., Shakhnarovich, G. (2012). Part annotations via pairwise correspondence. In 4th Workshop on Human Computation, AAAI.Google Scholar
  29. Mateus, D., Horaud, R., Knossow, D., Cuzzolin, F., & Boyer, E. (2008). Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Google Scholar
  30. McAuley, J., & Caetano, T. (2012). Fast matching of large point sets under occlusion. Pattern recognition, 45, 563–569.Google Scholar
  31. McAuley, J., Caetano, T., & Barbosa, M. S. (2008). Graph rigidity, cyclic belief propagation and point pattern matching. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 30(11), 2047–2054.Google Scholar
  32. Munkres, J. (1957). Algorithms for the assignment and transportation problems. Journal of the Society for Industrial and Applied Mathematics, 5(1), 32–38.CrossRefMATHMathSciNetGoogle Scholar
  33. Sharma, A., Horaud, R. P., Cech, J., & Boyer, E. (2011). Topologically-robust 3d shape matching based on diffusion geometry and seed growing. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  34. Starck, J., & Hilton, A. (2007). Correspondence labelling for wide-timeframe free-form surface matching. In International Conference on Computer Vision (ICCV).Google Scholar
  35. Tong, S., & Koller, D. (2000). Support vector machine active learning with applications to text classification. In International Conference on Machine Learning (ICML).Google Scholar
  36. Torresani, L., & Kolmogorov, V. (2008). Rother, C. Feature correspondence via graph matching: Models and global optimization. In European Conference on Computer Vision (ECCV).Google Scholar
  37. Umeyama, S. (1988). An eigendecomposition approach to weighted graph matching problems. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 10(5), 695–703.Google Scholar
  38. Vijayanarasimhan, S. (2011). Active visual category learning. PhD Thesis, UT Austin.Google Scholar
  39. Vijayanarasimhan, S., & Kapoor, A. (2010). Visual recognition and detection under bounded computational resources. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
  40. von Ahn, L., & Dabbish, L. (2004). Labeling images with a computer game. In CHI: SIGCHI Conference on Human Factors in Computing Systems. New York: ACM.Google Scholar
  41. Zass, R., & Shashua, A. (2008). Probabilistic graph and hypergraph matching. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.UC BerkeleyBerkeleyUSA
  2. 2.Microsoft Research RedmondRedmondUSA

Personalised recommendations