Automatic Segmentation of Unknown Objects, with Application to Baggage Security

  • Leo Grady
  • Vivek Singh
  • Timo Kohlberger
  • Christopher Alvino
  • Claus Bahlmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7573)


Computed tomography (CT) is used widely to image patients for medical diagnosis and to scan baggage for threatening materials. Automated reading of these images can be used to reduce the costs of a human operator, extract quantitative information from the images or support the judgements of a human operator. Object quantification requires an image segmentation to make measurements about object size, material composition and morphology. Medical applications mostly require the segmentation of prespecified objects, such as specific organs or lesions, which allows the use of customized algorithms that take advantage of training data to provide orientation and anatomical context of the segmentation targets. In contrast, baggage screening requires the segmentation algorithm to provide segmentation of an unspecified number of objects with enormous variability in size, shape, appearance and spatial context. Furthermore, security systems demand 3D segmentation algorithms that can quickly and reliably detect threats. To address this problem, we present a segmentation algorithm for 3D CT images that makes no assumptions on the number of objects in the image or on the composition of these objects. The algorithm features a new Automatic QUality Measure (AQUA) model that measures the segmentation confidence for any single object (from any segmentation method) and uses this confidence measure to both control splitting and to optimize the segmentation parameters at runtime for each dataset. The algorithm is tested on 27 bags that were packed with a large variety of different objects.


Ground Truth Image Segmentation Gaussian Mixture Model Segmentation Algorithm Object Segmentation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Vincent, L., Soille, P.: Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE PAMI 13(6), 583–598 (1991)CrossRefGoogle Scholar
  2. 2.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE PAMI 24(5), 603–619 (2002)CrossRefGoogle Scholar
  3. 3.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE PAMI 22(8), 888–905 (2000)CrossRefGoogle Scholar
  4. 4.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE PAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  5. 5.
    Li, Y., Sun, J., Tang, C., Shum, H.: Lazy snapping. In: Proc. of ACM SIGGRAPH 2004, pp. 303–308 (April 2004)Google Scholar
  6. 6.
    Endres, I., Hoiem, D.: Category Independent Object Proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 575–588. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Carreira, J., Sminchisescu, C.: Cpmc: Automatic object segmentation using constrained parametric min-cuts. IEEE PAMI 34, 1312–1328 (2012)CrossRefGoogle Scholar
  8. 8.
    Singh, S., Singh, M.: Explosives detection systems (EDS) for aviation security: A review. Signal Process 83(1), 31–55 (2003)zbMATHCrossRefGoogle Scholar
  9. 9.
    Smith, R., Connelly, J.: CT technologies (chapter 7). In: Aspects of Explosives Detection, pp. 131–145. Elsevier (2009)Google Scholar
  10. 10.
    ALERT (Awareness and Localization of Explosives-Related Threats), Northeastern University, ed.: Algorithm Development for Security Applications (ADSA) Workshops 1-6 (2008–2011)Google Scholar
  11. 11.
    Martz Jr., H.E., Crawford, C.: Overview of deployed EDS technologies. Technical report, LLNL-TR-417232, Lawrence Livermore National Laboratory (September 2009)Google Scholar
  12. 12.
    Grady, L., Schwartz, E.L.: Isoperimetric graph partitioning for image segmentation. IEEE PAMI 28(3), 469–475 (2006)CrossRefGoogle Scholar
  13. 13.
    Grady, L., Schwartz, E.L.: Isoperimetric partitioning: A new algorithm for graph partitioning. SIAM J. on Scientific Computing 27(6), 1844–1866 (2006)zbMATHMathSciNetCrossRefGoogle Scholar
  14. 14.
    Tuy, H.K.: A post-processing algorithm to reduce metallic clip artifacts in CT images. Eur. Radiol. 3, 129–134 (1993)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. PAM 42, 577–685 (1989)zbMATHMathSciNetGoogle Scholar
  16. 16.
    Tsai, A., Yezzi, A., Willsky, A.: Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification. IEEE Trans. on Image Proc. 10(8), 1169–1186 (2001)zbMATHCrossRefGoogle Scholar
  17. 17.
    Chan, T., Vese, L.: A level set algorithm for minimizing the Mumford-Shah functional in image processing. In: Workshop on VLSM, pp. 161–168. IEEE (2001)Google Scholar
  18. 18.
    Grady, L., Alvino, C.: The piecewise smooth Mumford-Shah functional on an arbitrary graph. IEEE TIP 18(11), 2547–2561 (2009)MathSciNetGoogle Scholar
  19. 19.
    Grady, L.: Fast, Quality, Segmentation of Large Volumes – Isoperimetric Distance Trees. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 449–462. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  20. 20.
    Blake, A., Zisserman, A.: Visual Reconstruction. MIT Press (1987)Google Scholar
  21. 21.
    Caselles, V., Kimmel, R., Sapiro, G., Sbert, C.: Minimal surfaces based object segmentation. IEEE Trans. on PAMI 19(4), 394–398 (1997)MathSciNetCrossRefGoogle Scholar
  22. 22.
    El-Zehiry, N., Grady, L.: Fast global optimization of curvature. In: Proc. of CVPR. IEEE Computer Society, IEEE (2010)Google Scholar
  23. 23.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. International Journal of Computer Vision 22, 61–79 (1997)zbMATHCrossRefGoogle Scholar
  24. 24.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proc. of ICCV, pp. 105–112 (2001)Google Scholar
  25. 25.
    Grady, L.: Random walks for image segmentation. IEEE PAMI 28(11), 1768–1783 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Leo Grady
    • 1
  • Vivek Singh
    • 2
  • Timo Kohlberger
    • 2
  • Christopher Alvino
    • 3
  • Claus Bahlmann
    • 2
  1. 1.HeartFlow, Inc.Redwood CityUSA
  2. 2.Corporate Research and TechnologyImaging and Computer Vision, Siemens CorporationPrincetonUSA
  3. 3.American Science and EngineeringBillericaUSA

Personalised recommendations