A Multi-stage Approach to Curve Extraction

  • Yuliang Guo
  • Naman Kumar
  • Maruthi Narayanan
  • Benjamin Kimia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8689)

Abstract

We propose a multi-stage approach to curve extraction where the curve fragment search space is iteratively reduced by removing unlikely candidates using geometric constrains, but without affecting recall, to a point where the application of an objective functional becomes appropriate. The motivation in using multiple stages is to avoid the drawback of using a global functional directly on edges, which can result in non-salient but high scoring curve fragments, which arise from non-uniformly distributed edge evidence. The process progresses in stages from local to global: (i) edges, (ii) curvelets, (iii) unambiguous curve fragments, (iv) resolving ambiguities to generate a full set of curve fragment candidates, (v) merging curve fragments based on a learned photometric and geometric cues as well a novel lateral edge sparsity cue, and (vi) the application of a learned objective functional to get a final selection of curve fragments. The resulting curve fragments are typically visually salient and have been evaluated in two ways. First, we measure the stability of curve fragments when images undergo visual transformations such as change in viewpoints, illumination, and noise, a critical factor for curve fragments to be useful to later visual processes but one often ignored in evaluation. Second, we use a more traditional comparison against human annotation, but using the CFGD dataset and CFGD evaluation strategy rather than the standard BSDS counterpart, which is shown to be not appropriate for evaluating curve fragments. Under both evaluation schemes our results are significantly better than those state of the art algorithms whose implementations are publicly available.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aanæs, H., Dahl, A.L., Pedersen, K.S.: Interesting interest points - a comparative study of interest point performance on a unique data set. International Journal of Computer Vision 97(1), 18–35 (2012)CrossRefGoogle Scholar
  2. 2.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)CrossRefGoogle Scholar
  3. 3.
    Baker, S., Nayar, S.: Global measures of coherence for edge detector evaluation. In: CVPR, pp. II:373–II:379 (1999)Google Scholar
  4. 4.
    Coughlan, J.M., Yuille, A.L.: Bayesian a* tree search with expected o(n) node expansions: Applications to road tracking. Neural Computation 14(8), 1929–1958 (2002)CrossRefMATHGoogle Scholar
  5. 5.
    Felzenszwalb, P., McAllester, D.: A min-cover approach for finding salient curves. In: Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2006, p. 185 (June 2006)Google Scholar
  6. 6.
    Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. IEEE Trans. Pattern Analysis and Machine Intelligence 30(1), 36–51 (2008)CrossRefGoogle Scholar
  7. 7.
    Fidler, S., Berginc, G., Leonardis, A.: Hierarchical statistical learning of generic parts of object structure. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 182–189. IEEE Computer Society (2006)Google Scholar
  8. 8.
    Fischler, M., Tenenbaum, J., Wolf, H.: Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique. Computer Graphics and Image Processing 15(3), 201–223Google Scholar
  9. 9.
    Geman, D., Jedynak, B.: An active testing model for tracking roads in satellite images. IEEE Trans. Pattern Anal. Mach. Intell. 18(1), 1–14 (1996)CrossRefGoogle Scholar
  10. 10.
    Guo, Y., Kimia, B.B.: On evaluating methods for recovering image curve fragments. In: Proceedings of IEEE Workshop on Perceptual Organization in Computer Vision, POCV, pp. 9–16 (June 2012)Google Scholar
  11. 11.
    Hu, W., Wu, Y.N., Zhu, S.C.: Image representation by active curves. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1808–1815 (2011)Google Scholar
  12. 12.
    Iverson, L., Zucker, S.: Logical/linear operators for image curves. PAMI 17(10), 982–996 (1995)CrossRefGoogle Scholar
  13. 13.
    Kennedy, R., Gallier, J., Shi, J.: Contour cut: Identifying salient contours in images by solving a hermitian eigenvalue problem. In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, pp. 2065–2072. IEEE Computer Society (2011)Google Scholar
  14. 14.
    Kokkinos, I.: Highly accurate boundary detection and grouping. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2520–2527. IEEE Computer Society Press, San Francisco (2010)Google Scholar
  15. 15.
    Kovesi, P.D.: MATLAB and Octave functions for computer vision and image processing. School of Computer Science & Software Engineering, The University of Western Australia (2009), http://www.csse.uwa.edu.au/~pk/research/matlabfns/
  16. 16.
    Lin, L., Zeng, K., Liu, X., Zhu, S.C.: Layered graph matching by composite cluster sampling with collaborative and competitive interactions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1351–1358. IEEE Computer Society Press, Miami (2009)Google Scholar
  17. 17.
    Mahamud, S., Williams, L., Thornber, K., Xu, K.: Segmentation of multiple salient closed contours from real images. PAMI 25(4), 433–444 (2003)CrossRefGoogle Scholar
  18. 18.
    Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(5), 530–549 (2004)CrossRefGoogle Scholar
  19. 19.
    Narayanan, M., Kimia, B.: To complete or not to complete: Gap completion in real images. In: Proceedings of IEEE Workshop on Perceptual Organization in Computer Vision, POCV, pp. 47–54 (June 2012)Google Scholar
  20. 20.
    Payet, N., Todorovic, S.: From a set of shapes to object discovery. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 57–70. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  21. 21.
    Payet, N., Todorovic, S.: From contours to 3D object detection and pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 983–990 (2011)Google Scholar
  22. 22.
    Payet, N., Todorovic, S.: Sledge: Sequential labeling of image edges for boundary detection. International Journal of Computer Vision 104(1), 15–37 (2013)CrossRefMATHMathSciNetGoogle Scholar
  23. 23.
    Ren, X., Fowlkes, C., Malik, J.: Learning probabilistic models for contour completion in natural images. International Journal of Computer Vision 77(1-3), 47–63 (2008)CrossRefGoogle Scholar
  24. 24.
    Sharon, E., Brandt, A., Basri, R.: Segmentation and boundary detection using multiscale intensity measurements. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, December 9-14, pp. 469–476. IEEE Computer Society Press, Kauai (2001)Google Scholar
  25. 25.
    Shashua, A., Ullman, S.: Structural saliency: The detection of globally salient structures using a locally connected network. In: ICCV, pp. 321–327 (1988)Google Scholar
  26. 26.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 731–737. IEEE Computer Society (1997)Google Scholar
  27. 27.
    Tamrakar, A., Kimia, B.B.: No grouping left behind: From edges to curve fragments. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Computer Society, Rio de Janeiro (2007)Google Scholar
  28. 28.
    Widynski, N., Mignotte, M.: A particle filter framework for contour detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 780–793. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  29. 29.
    Yu, S.X., Shi, J.: Multiclass spectral clustering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 313–319. IEEE Computer Society, Nice (2003)CrossRefGoogle Scholar
  30. 30.
    Zhu, Q., Song, G., Shi, J.: Untangling cycles for contour grouping. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1–8. IEEE Computer Society (2007)Google Scholar
  31. 31.
    Zhu, Q., Wang, L., Wu, Y., Shi, J.: Contour context selection for object detection: A set-to-set contour matching approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 774–787. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Yuliang Guo
    • 1
  • Naman Kumar
    • 1
  • Maruthi Narayanan
    • 1
  • Benjamin Kimia
    • 1
  1. 1.School of EngineeringBrown UniversityProvidenceUSA

Personalised recommendations