Pattern Recognition and Image Analysis

, Volume 19, Issue 2, pp 277–283 | Cite as

Pearling: Stroke segmentation with crusted pearl strings

  • B. Whited
  • J. Rossignac
  • G. Slabaugh
  • T. Fang
  • G. Unal
Application Problems

Abstract

We introduce a novel segmentation technique, called Pearling, for the semi-automatic extraction of idealized models of networks of strokes (variable width curves) in images. These networks may for example represent roads in an aerial photograph, vessels in a medical scan, or strokes in a drawing. The operator seeds the process by selecting representative areas of good (stroke interior) and bad colors. Then, the operator may either provide a rough trace through a particular path in the stroke graph or simply pick a starting point (seed) on a stroke and a direction of growth. Pearling computes in realtime the centerlines of the strokes, the bifurcations, and the thickness function along each stroke, hence producing a purified medial axis transform of a desired portion of the stroke graph. No prior segmentation or thresholding is required. Simple gestures may be used to trim or extend the selection or to add branches. The realtime performance and reliability of Pearling results from a novel disk-sampling approach, which traces the strokes by optimizing the positions and radii of a discrete series of disks (pearls) along the stroke. A continuous model is defined through subdivision. By design, the idealized pearl string model is slightly wider than necessary to ensure that it contains the stroke boundary. A narrower core model that fits inside the stroke is computed simultaneously. The difference between the pearl string and its core contains the boundary of the stroke and may be used to capture, compress, visualize, or analyze the raw image data along the stroke boundary.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    C. Kirbas and F. Quek, “A Review of Vessel Extraction Techniques and Algorithms,” ACM Comp. Surv. 36(2), 81 (2004).CrossRefGoogle Scholar
  2. 2.
    J. A. Tyrrell, E. di Tomaso, D. Fuja, et al., Robust 3-D “Modeling of Vasculature Imagery Using Superellipsoids,” IEEE Trans. Med. Imaging 26(2), 223 (2007).CrossRefGoogle Scholar
  3. 3.
    L. M. Lorigo, O. D. Faugeras, W. E. L. Gnmson, et al., “CURVES: Curve Evolution for Vessel Segmentation,” Med. Image Anal. 5, 195 (2001).CrossRefGoogle Scholar
  4. 4.
    J. Soares, J. Leandro, R. Cesar, et al., “Retinal Vessel Segmentation Using the 2-D Gabor Wavelet and Supervised Classification,” IEEE Trans. Med. Imaging 25(9), 1214 (2006).CrossRefGoogle Scholar
  5. 5.
    O. Wink, W. Niessen, and M. A. Viergever, “Fast Delineation and Visualization of Vessels in 3-D Angiographic Images,” IEEE Trans. Med. Imaging 19(4), 337 (2000).CrossRefGoogle Scholar
  6. 6.
    A. Szymczak, A. Tannenbaum, and K. Mischaikow, “Coronary Vessel Cores from 3D Imagery: A Topological Approach,” in Medical Imaging 2005: Image Processing. Proceedings of the SPIE (2005), Vol. 5747, pp. 505–513.Google Scholar
  7. 7.
    P. Medek, P. Benes, and J. Sochor, “Computation of Tunnels in Protein Molecules Using Delaunay Triangulation,” in Journal of WSCG (2007), p. 8.Google Scholar
  8. 8.
    L. Costa. and R. Cesar, Shape Analysis and Classification (CRC Press, 2001).Google Scholar
  9. 9.
    A. Telea and J. J. van Wijk, “An Augmented Fast Marching Method for Computing Skeletons and Centerlines,” in Symposium on Data Visualisation (2002), pp. 251–259.Google Scholar
  10. 10.
    C. Pudney, “Distance-Ordered Homotopic Thinning: A Skeletonization Algorithm for 3D Digital Images,” IEEE. Trans. Biomed. Eng. 72(3), 404 (1998).Google Scholar
  11. 11.
    M. Van Dortmont, H. van de Wetering, and A. Telea, “Skeletonization and Distance Transforms of 3D Volumes Using Graphics Hardware,” in DGCI, pp. 617–629 (2006).Google Scholar
  12. 12.
    N. Cornea, D. Silver, X. Yuan, and R. Balasubramanian, “Computing Hierarchical Curve-Skeletons of 3D Objects,” The Visual Computer 21(11), 945 (2005).CrossRefGoogle Scholar
  13. 13.
    H. Li and A. Yezzi, “Vessels as 4D Curves: Global Minimal 4D Paths to 3D Tubular Structure Extraction, in: Workshop on Mathematical Methods in Biomedical Image Analysis (2006).Google Scholar
  14. 14.
    L. D. Cohen and R. Kimmel, “Global Minimum for Active Contours Models: A Minimal Path Approach,” Int. J. Comp. Vis. 24(1), 57 (1997).CrossRefGoogle Scholar
  15. 15.
    H. Blum, “A Transformation for Extracting New Descriptors of Shape,” in Models for the Perception of Speech and Visual Form, Ed. by W. Wathen-Dunn (MIT Press, Cambridge, 1967), pp. 362–380.Google Scholar
  16. 16.
    B. Whited, J. Rossignac, G. Slabaugh, T. Fang, and G. Una, “Pearling: 3D Interactive Extraction of Tubular Structures from Volumetric Images,” in MICCAI Workshop, Interaction in Medical Image Analysts and Visualization (2007).Google Scholar
  17. 17.
    G. Monge, Applications de 1’analyse à la géométrie, 5th ed. (Bachelier, Paris, 1894).Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2009

Authors and Affiliations

  • B. Whited
    • 1
  • J. Rossignac
    • 1
  • G. Slabaugh
    • 2
  • T. Fang
    • 2
  • G. Unal
    • 2
  1. 1.Georgia Institute of Technology, Graphics, Visualization and Usability CenterAtlantaUSA
  2. 2.Intelligent Vision and Reasoning DepartmentSiemens Corporate ResearchPrincetonUSA

Personalised recommendations