PointFlow: A Model for Automatically Tracing Object Boundaries and Inferring Illusory Contours

  • Fang YangEmail author
  • Alfred M. Bruckstein
  • Laurent D. Cohen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10746)


In this paper, we propose a novel method for tracing object boundaries automatically based on a method called “PointFlow” in image induced vector fields. The PointFlow method comprises two steps: edge detection and edge integration. Basically, it uses an ordinary differential equation for describing the movement of points under the action of an image-induced vector field and generates induced trajectories. The trajectories of the flows allow to find and integrate edges and determine object boundaries. We also extend the original PointFlow method to make it adaptable to images with complicated scenes. In addition, the PointFlow method can be applied to infer certain illusory contours.

We test our method on real image dataset. Compared with the other classical edge detection and integration models, our PointFlow method is better at providing precise and continuous curves. The experimental results clearly exhibit the robustness and effectiveness of the proposed method.


Automatically tracing object boundaries Induced vector field PointFlow Differential equations Illusory contours 


  1. 1.
    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
  2. 2.
    Butcher, J.C.: Numerical methods for ordinary differential equations in the 20th century. J. Comput. Appl. Math. 125(1), 1–29 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Duda, R.O., Hart, P.E.: Use of the hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11–15 (1972)CrossRefzbMATHGoogle Scholar
  4. 4.
    Eua-Anant, N., Udpa, L.: Boundary detection using simulation of particle motion in a vector image field. IEEE Trans. Image Process. 8(11), 1560–1571 (1999)CrossRefGoogle Scholar
  5. 5.
    Kimmel, R., Bruckstein, A.M.: Regularized laplacian zero crossings as optimal edge integrators. Int. J. Comput. Vis. 53(3), 225–243 (2003)CrossRefGoogle Scholar
  6. 6.
    Lu, C., Chi, Z., Chen, G., Feng, D.: Geometric analysis of particle motion in a vector image field. J. Math. Imaging Vis. 26(3), 301–307 (2006)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Makhervaks, V., Barequet, G., Bruckstein, A.: Image flows and one-liner graphical image representation. Ann. N.Y. Acad. Sci. 972(1), 10–18 (2002)CrossRefGoogle Scholar
  8. 8.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceeding on 8th International Conference of Computer Vision, vol. 2, pp. 416–423, July 2001Google Scholar
  9. 9.
    Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. Pattern Anal. Mach. Intell. 26(5), 530–549 (2004)CrossRefGoogle Scholar
  10. 10.
    Rubner, Y., Tomasi, C.: Coalescing texture descriptors. In: ARPA Image Understanding, Workshop, pp. 927–935 (1996)Google Scholar
  11. 11.
    Von Der Heyclt, R., Peterhans, E., Baurngartner, G.: Illusory contours and cortical neuron responses. Science 224, 1260–1262 (1984)CrossRefGoogle Scholar
  12. 12.
    Ziou, D., Tabbone, S.: Edge detection techniques - an overview. Int. J. Pattern Recogn. Image Anal. 8, 537–559 (1998)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Fang Yang
    • 1
    Email author
  • Alfred M. Bruckstein
    • 2
  • Laurent D. Cohen
    • 1
  1. 1.CEREMADE, CNRS, UMR 7534, Université Paris Dauphine, PSL Research UniversityParisFrance
  2. 2.Computer Science DepartmentTechnion – IITHaifaIsrael

Personalised recommendations