Efficient Computation of Attributes and Saliency Maps on Tree-Based Image Representations

  • Yongchao Xu
  • Edwin Carlinet
  • Thierry Géraud
  • Laurent Najman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9082)

Abstract

Tree-based image representations are popular tools for many applications in mathematical morphology and image processing. Classically, one computes an attribute on each node of a tree and decides whether to preserve or remove some nodes upon the attribute function. This attribute function plays a key role for the good performance of tree-based applications. In this paper, we propose several algorithms to compute efficiently some attribute information. The first one is incremental computation of information on region, contour, and context. Then we show how to compute efficiently extremal information along the contour (e.g., minimal gradient’s magnitude along the contour). Lastly, we depict computation of extinction-based saliency map using tree-based image representations. The computation complexity and the memory cost of these algorithms are analyzed. To the best of our knowledge, except information on region, none of the other algorithms is presented explicitly in any state-of-the-art paper.

Keywords

Min/Max-tree Tree of shapesa Algorithm Attribute Saliency map 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Berger, C., Géraud, T., Levillain, R., Widynski, N., Baillard, A., Bertin, E.: Effective component tree computation with application to pattern recognition in astronomical imaging. In: Proc. of IEEE ICIP., vol. 4, pp. 41–44 (2007)Google Scholar
  2. 2.
    Breen, E., Jones, R.: Attribute openings, thinnings, and granulometries. CVIU 64(3), 377–389 (1996)Google Scholar
  3. 3.
    Cao, F., Musé, P., Sur, F.: Extracting meaningful curves from images. JMIV 22, 159–181 (2005)CrossRefGoogle Scholar
  4. 4.
    Carlinet, E., Géraud, T.: A comparative review of component tree computation algorithms. IEEE Transactions on Image Processing 23(9), 3885–3895 (2014)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Carlinet, E., Géraud, T.: A color tree of shapes with illustrations on filtering, simplification, and segmentation (submitted for publication, 2015)Google Scholar
  6. 6.
    Caselles, V., Monasse, P.: Geometric Description of Images as Topographic Maps, 1st edn. Springer Publishing Company, Incorporated (2009)Google Scholar
  7. 7.
    Desolneux, A., Moisan, L., Morel, J.: Edge detection by helmholtz principle. JMIV 14(3), 271–284 (2001)CrossRefMATHGoogle Scholar
  8. 8.
    Géraud, T., Carlinet, E., Crozet, S., Najman, L.: A quasi-linear algorithm to compute the tree of shapes of nD images. In: Hendriks, C.L.L., Borgefors, G., Strand, R. (eds.) ISMM 2013. LNCS, vol. 7883, pp. 98–110. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  9. 9.
    Monasse, P., Guichard, F.: Fast computation of a contrast-invariant image representation. IEEE Trans. on Image Processing 9(5), 860–872 (2000)CrossRefGoogle Scholar
  10. 10.
    Najman, L., Couprie, M.: Building the component tree in quasi-linear time. IEEE Trans. on Image Processing 15(11), 3531–3539 (2006)CrossRefGoogle Scholar
  11. 11.
    Nistér, D., Stewénius, H.: Linear time maximally stable extremal regions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 183–196. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  12. 12.
    Ouzounis, G.K., Wilkinson, M.H.F.: A parallel implementation of the dual-input max-tree algorithm for attribute filtering. In: ISMM, pp. 449–460 (2007)Google Scholar
  13. 13.
    Salembier, P., Oliveras, A., Garrido, L.: Antiextensive connected operators for image and sequence processing. ITIP 7(4), 555–570 (1998)Google Scholar
  14. 14.
    Salembier, P., Wilkinson, M.H.F.: Connected operators. IEEE Signal Processing Mag. 26(6), 136–157 (2009)CrossRefGoogle Scholar
  15. 15.
    Song, Y.: A topdown algorithm for computation of level line trees. IEEE Transactions on Image Processing 16(8), 2107–2116 (2007)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Vachier, C., Meyer, F.: Extinction values: A new measurement of persistence. In: IEEE Workshop on Non Linear Signal/Image Processing, pp. 254–257 (1995)Google Scholar
  17. 17.
    Westenberg, M.A., Roerdink, J.B.T.M., Wilkinson, M.H.F.: Volumetric attribute filtering and interactive visualization using the max-tree representation. ITIP 16(12), 2943–2952 (2007)MathSciNetGoogle Scholar
  18. 18.
    Wilkinson, M.H.F.: A fast component-tree algorithm for high dynamic-range images and second generation connectivity. In: Proc. of ICIP, pp. 1021–1024 (2011)Google Scholar
  19. 19.
    Wilkinson, M.H.F., Gao, H., Hesselink, W.H., Jonker, J.E., Meijster, A.: Concurrent computation of attribute filters on shared memory parallel machines. PAMI 30(10), 1800–1813 (2008)CrossRefGoogle Scholar
  20. 20.
    Xu, Y.: Tree-based shape spaces: Definition and applications in image processing and computer vision. Ph.D. thesis, Université Paris Est, Marne-la-Vallée, France (December 2013)Google Scholar
  21. 21.
    Xu, Y., Géraud, T., Najman, L.: Context-based energy estimator: Application to object segmentation on the tree of shapes. In: ICIP, pp. 1577–1580. IEEE (2012)Google Scholar
  22. 22.
    Xu, Y., Géraud, T., Najman, L.: Two applications of shape-based morphology: Blood vessels segmentation and a generalization of constrained connectivity. In: Hendriks, C.L.L., Borgefors, G., Strand, R. (eds.) ISMM 2013. LNCS, vol. 7883, pp. 390–401. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  23. 23.
    Xu, Y., Géraud, T., Najman, L.: Morphological Filtering in Shape Spaces: Applications using Tree-Based Image Representations. In: ICPR, pp. 485–488 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Yongchao Xu
    • 1
    • 2
  • Edwin Carlinet
    • 1
    • 2
  • Thierry Géraud
    • 1
  • Laurent Najman
    • 2
  1. 1.EPITA Research and Development Laboratory (LRDE)Lekremlin-BicetneFrance
  2. 2.LIGM, Équipe A3SI, ESIEE ParisUniversité Paris-EstParisFrance

Personalised recommendations