Advertisement

A Persistence-Based Approach to Automatic Detection of Line Segments in Images

  • Vitaliy Kurlin
  • Grzegorz Muszynski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11382)

Abstract

Edge detection algorithms usually produce a discrete set of edgels (edge pixels) in a given image on a fixed pixel grid. We consider the harder problem of detecting continuous straight line segments at subpixel resolution. The state-of-the art Line Segment Detection Algorithm (LSDA) outputs unordered line segments whose total number cannot be easily controlled. Another motivation to improve the LSDA is to avoid intersections and small angles between line segments, hence difficulties in higher level tasks such as segmentation or contour extraction.

The new Persistent Line Segment Detector (PLSD) outputs only non-intersecting line segments and ranks them by a strength, hence the user can choose a number of segments. The main novelty is an automatic selection of strongest segments along any straight line by using the persistence from Topological Data Analysis. The experiments on the Berkeley Segmentation Database of 500 real-life images show that the new algorithm outperforms the LSDA on the important measure of Boundary Recall.

Keywords

Topological persistence Edge detection Skeletonization 

Notes

Acknowledgments

We thank all reviewers for helpful suggestions. This work was supported by the EPSRC grant “Application-driven Topological Data Analysis” (EP/R018472/1).

References

  1. 1.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. Trans. PAMI 33, 898–916 (2011)CrossRefGoogle Scholar
  2. 2.
    Ballard, D.: Generalizing the hough transform to detect arbitrary shapes. Pattern Recogn. 13, 111–122 (1981)CrossRefGoogle Scholar
  3. 3.
    Canny, J.: A computational approach to edge detection. Trans. PAMI 8, 679–698 (1986)CrossRefGoogle Scholar
  4. 4.
    Chernov, A., Kurlin, V.: Reconstructing persistent graph structures from noisy images. Image-A 3, 19–22 (2013)Google Scholar
  5. 5.
    Cohen-Steiner, D., Edelsbrunner, H., Harer, J.: Stability of persistence diagrams. Discrete Comput. Geom. 37, 103–130 (2007)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Duan, L., Lafarge, F.: Image partitioning into convex polygons. In: Proceedings of CVPR (Computer Vision and Pattern Recognition), pp. 3119–3127 (2015)Google Scholar
  7. 7.
    Edelsbrunner, H., Harer, J.: Computational Topology: An Introduction. AMS, Providence (2010)zbMATHGoogle Scholar
  8. 8.
    Forsythe, J., Kurlin, V.: Convex constrained meshes for superpixel segmentations of images. J. Electron. Imaging 26(6), 061609 (2017)CrossRefGoogle Scholar
  9. 9.
    Forsythe, J., Kurlin, V., Fitzgibbon, A.: Resolution-independent superpixels based on convex constrained meshes without small angles. In: Bebis, G., et al. (eds.) ISVC 2016. LNCS, vol. 10072, pp. 223–233. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-50835-1_21CrossRefGoogle Scholar
  10. 10.
    Grompone von Gioi, R.: A Contrario Line Segment Detection. Briefs in Computer Science. Springer, New York (2014).  https://doi.org/10.1007/978-1-4939-0575-1CrossRefzbMATHGoogle Scholar
  11. 11.
    Grompone von Gioi, R., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a line segment detector. Image Process. Line 2, 35–55 (2012)CrossRefGoogle Scholar
  12. 12.
    Kahn, P., Kitchen, L., Riseman, E.: A fast line finder for vision-guided robot navigation. Trans. PAMI 12, 1098–1102 (1990)CrossRefGoogle Scholar
  13. 13.
    Kalisnik, S., Kurlin, V., Lesnik, D.: A high-dimensional homologically persistent skeleton. Adv. Appl. Math. 102, 113–142 (2019)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Kurlin, V.: Auto-completion of contours in sketches, maps and sparse 2D images based on topological persistence. In: Proceedings of SYNASC 2014 Workshop CTIC: Computational Topology in Image Context, pp. 594–601. IEEE (2014)Google Scholar
  15. 15.
    Kurlin, V.: A homologically persistent skeleton is a fast and robust descriptor of interest points in 2d images. In: Azzopardi, G., Petkov, N. (eds.) CAIP 2015. LNCS, vol. 9256, pp. 606–617. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-23192-1_51CrossRefGoogle Scholar
  16. 16.
    Kurlin, V.: A one-dimensional homologically persistent skeleton of a point cloud in any metric space. Comput. Graph. Forum 34, 253–262 (2015)CrossRefGoogle Scholar
  17. 17.
    Kurlin, V.: A fast persistence-based segmentation of noisy 2d clouds with provable guarantees. Pattern Recogn. Lett. 83, 3–12 (2016)CrossRefGoogle Scholar
  18. 18.
    Tarjan, R.: Data Structures and Network Algorithms. SIAM, Philadelphia (1983)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of LiverpoolLiverpoolUK
  2. 2.Lawrence Berkeley National LaboratoryBerkeleyUSA

Personalised recommendations