Graph Cut Approaches for Materials Segmentation Preserving Shape, Appearance, and Topology

  • Jarrell W. Waggoner
  • Jeff Simmons
  • Marc De Graef
  • Song Wang
Conference paper


Segmenting material images into underlying objects is an important but challenging problem given object complexity and image noise. Consistency of shape, appearance, and topology among the underlying objects are critical properties of materials images and can be considered as criteria to improve segmentation. For example, some materials may have objects with a specific shape or appearance in each serial section slice, which only changes minimally from slice to slice; and some materials may exhibit specific interobject topology which constrains their neighboring relations. In this paper, we develop new graph-cut based approaches for materials science image segmentation. Specifically, these approaches segment image volumes by repeatedly propagating a 2D segmentation from one slice to another. We introduce different terms into the graph-cut cost function to enforce desirable shape, appearance, and topology consistency. We justify the effectiveness of the proposed approaches by using them to segment sequences of serial-section images of different materials.


segmentation propagation shape appearance topology graph cut 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Y. Boykov and V. Kolmogorov. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26 (9) (2004), pp. 1124–1137.CrossRefGoogle Scholar
  2. [2]
    Y. Boykov, O. Veksler, and R. Zabih. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23 (11) (2001), pp. 1222–1239.CrossRefGoogle Scholar
  3. [3]
    V. Kolmogorov and R. Zabih. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26 (2) (2004), pp. 147–159.CrossRefGoogle Scholar
  4. [4]
    J. Waggoner, J. Simmons, and S. Wang. Proceedings of SPIE (Computational Imaging X), vol. 8296 (Burlingame, CA, 2012).Google Scholar
  5. [5]
    O. Veksler. Efficient graph-based energy minimization methods in computer vision. Ph.D. thesis, Cornell University, Ithaca, NY, USA, 1999.Google Scholar
  6. [6]
    R. K. Ahuja, T. L. Magnanti, and J. B. Orlin. Network Flows: Theory, Algorithms, & Applications (Englewood Cliffs: Prentice Hall).Google Scholar
  7. [7]
    J. MacSleyne, M. Uchic, J. Simmons, and M. D. Graef. Acta Materialia, 57 (2009), pp. 6251–6267.CrossRefGoogle Scholar
  8. [8]
    M. Groeber, S. Ghosh, M. D. Uchic, and D. M. Dimiduk. JOM Journal of the Minerals, Metals and Materials Society, 59 (2007), pp. 32–36.CrossRefGoogle Scholar
  9. [9]
    L. Lam, S.-W. Lee, and C. Y. Suen. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14 (9) (1992), pp. 869–885.CrossRefGoogle Scholar
  10. [10]
    D. Rowenhorst, A. Gupta, C. Feng, and G. Spanos. Scripta Materialia, 55 (1) (2006), pp. 11–16.CrossRefGoogle Scholar
  11. [11]
    C. H. P. Lupis. Chemical Thermodynamics of Materials (Elsevier, 1983).Google Scholar
  12. [12]
    D. Rowenhorst, A. Lewis, and G. Spanos. Acta Materialia, 58 (2010), pp. 5511–5519.CrossRefGoogle Scholar

Copyright information

© TMS (The Minerals, Metals & Materials Society) 2012

Authors and Affiliations

  • Jarrell W. Waggoner
    • 1
  • Jeff Simmons
    • 2
  • Marc De Graef
    • 3
  • Song Wang
    • 1
  1. 1.Department of Engineering and ComputingUniversity of South CarolinaColumbiaUSA
  2. 2.Materials and Manufacturing DirectorateAir Force Research LabsDaytonUSA
  3. 3.Department of Materials Science and EngineeringCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations