Fast and Robust Active Contours Model for Image Segmentation

  • Yupeng Li
  • Guo Cao
  • Qian Yu
  • Xuesong Li


Image segmentation using local region-based active contour models can segment images with intensity inhomogeneity effectively, but their segmentation results are sensitive to the initialization and easy to get incorrect results when dealing with texture images. This paper presents a novel active contour model (ACM) for image segmentation. The proposed method adopts local kernel mapping to enhance the discriminative ability to delineate nonlinear decision boundaries between classes. In addition, we introduce a modified convex model and propose a fast evolving scheme accordingly to deal with the minimization of the model energy function. The proposed approach is validated by a comparative study over a large number of experiments on synthetic and real images. The experiments demonstrate that our method is more efficient and robust for segmenting different kinds of images compared with the state-of-the-art image segmentation methods.


Convex Active contour model Image segmentation Local kernel mapping Fast Robust 



This work has been partially supported by National Science Foundation of China (6100318, 61371168), National High Technology Research and Development Program of China (No. 2013AA014604), National key research and development program of China (2016YFC0801304, 2017YFC0803705), Jiangsu Province Regular Institutions of Higher Learning Academic Degree Graduate Student Innovation Plan (KYZZ16_0192).


  1. 1.
    Osher S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations. J Comput Phys 79(1):12–49MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Ayed IB, Mitiche A, Belhadj Z (2005) Multiregion level-set partitioning of synthetic aperture radar images. IEEE Trans Pattern Anal Mach Intell 27(5):793–800CrossRefGoogle Scholar
  3. 3.
    Ben Ayed I, Mitiche A, Belhadj Z (2006) Polarimetric image segmentation via maximum-likelihood approximation and efficient multiphase level-sets. IEEE Trans Pattern Anal Mach Intell 28(9):1493–1500CrossRefGoogle Scholar
  4. 4.
    Ben Salah M, Mitiche A, Ben Ayed I (2010) Effective level set image segmentation with a kernel induced data term. IEEE Trans Image Process 19(1):220–232MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Ayed IB, Mitiche A (2008) A region merging prior for variational level set image segmentation. IEEE Trans Image Process 17(12):2301–2311MathSciNetzbMATHCrossRefGoogle Scholar
  6. 6.
    Wang XF, Min H, Zou L et al (2015) A novel level set method for image segmentation by incorporating local statistical analysis and global similarity measurement. Pattern Recogn 48(1):189–204CrossRefGoogle Scholar
  7. 7.
    Wang L, He L, Mishra A et al (2009) Active contours driven by local Gaussian distribution fitting energy. Sig Process 89(12):2435–2447zbMATHCrossRefGoogle Scholar
  8. 8.
    Malladi R, Sethian J, Vemuri BC (1995) Shape modeling with front propagation: a level set approach. IEEE Trans Pattern Anal Mach Intell 17(2):158–175CrossRefGoogle Scholar
  9. 9.
    Li C, Xu C, Gui C et al (2005) Level set evolution without re-initialization: a new variational formulation. In: IEEE computer society conference on computer vision and pattern recognition, 2005. CVPR 2005. IEEE, 2005, vol 1, pp 430–436Google Scholar
  10. 10.
    Vasilevskiy A, Siddiqi K (2002) Flux maximizing geometric flows. IEEE Trans Pattern Anal Mach Intell 24(12):1565–1578zbMATHCrossRefGoogle Scholar
  11. 11.
    Yang X, Gao X, Li J et al (2014) A shape-initialized and intensity-adaptive level set method for auroral oval segmentation. Inf Sci 277:794–807CrossRefGoogle Scholar
  12. 12.
    Wang Y, Xiang S, Pan C et al (2013) Level set evolution with locally linear classification for image segmentation. Pattern Recogn 46(6):1734–1746zbMATHCrossRefGoogle Scholar
  13. 13.
    Zhao YQ, Wang XH, Wang XF et al (2014) Retinal vessels segmentation based on level set and region growing. Pattern Recogn 47(7):2437–2446CrossRefGoogle Scholar
  14. 14.
    Thapaliya K, Pyun JY, Park CS et al (2013) Level set method with automatic selective local statistics for brain tumor segmentation in MR images. Comput Med Imaging Graph 37(7):522–537CrossRefGoogle Scholar
  15. 15.
    Wang XF, Min H, Zhang YG (2015) Multi-scale local region based level set method for image segmentation in the presence of intensity inhomogeneity. Neurocomputing 151:1086–1098CrossRefGoogle Scholar
  16. 16.
    Wang L, Shi F, Li G et al (2014) Segmentation of neonatal brain MR images using patch-driven level sets. NeuroImage 84:141–158CrossRefGoogle Scholar
  17. 17.
    Cote M, Saeedi P (2013) Automatic rooftop extraction in nadir aerial imagery of suburban regions using corners and variational level set evolution. IEEE Trans Geosci Remote Sens 51(1):313–328CrossRefGoogle Scholar
  18. 18.
    Andersson T, Lathen G, Lenz R et al (2013) Modified gradient search for level set based image segmentation. IEEE Trans Image Process 22(2):621–630MathSciNetzbMATHCrossRefGoogle Scholar
  19. 19.
    Wang L, Pan C (2014) Robust level set image segmentation via a local correntropy-based K-means clustering. Pattern Recogn 47(5):1917–1925CrossRefGoogle Scholar
  20. 20.
    Le T, Luu K, Savvides M (2013) SparCLeS: dynamic sparse classifiers with level sets for robust beard/moustache detection and segmentation. IEEE Trans Image Process 22(8):3097–3107CrossRefGoogle Scholar
  21. 21.
    Hao M, Shi W, Zhang H et al (2014) Unsupervised change detection with expectation-maximization-based level set. IEEE Geosci Remote Sens Lett 11(1):210–214CrossRefGoogle Scholar
  22. 22.
    Yang X, Gao X, Tao D et al (2015) An efficient MRF embedded level set method for image segmentation. IEEE Trans Image Process 24(1):9–21MathSciNetCrossRefGoogle Scholar
  23. 23.
    Chan TF, Vese L (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277zbMATHCrossRefGoogle Scholar
  24. 24.
    Piovano J, Rousson M, Papadopoulo T (2007) Efficient segmentation of piecewise smooth images. In: Scale space and variational methods in computer vision. Springer, Berlin, Heidelberg, 2007, pp 709–720Google Scholar
  25. 25.
    Li C, Kao C Y, Gore JC et al (2007) Implicit active contours driven by local binary fitting energy. In: IEEE conference on computer vision and pattern recognition, 2007. CVPR’07. IEEE, pp 1–7Google Scholar
  26. 26.
    Wang L, He L, Mishra A et al (2009) Active contours driven by local Gaussian distribution fitting energy. Signal Process 89(12):2435–2447zbMATHCrossRefGoogle Scholar
  27. 27.
    Paragios N, Deriche R (2002) Geodesic active regions and level set methods for supervised texture segmentation]. Int J Comput Vis 46(3):223–247zbMATHCrossRefGoogle Scholar
  28. 28.
    Wang XF, Huang DS, Xu H (2010) An efficient local Chan–Vese model for image segmentation. Pattern Recogn 43(3):603–618zbMATHCrossRefGoogle Scholar
  29. 29.
    Sun K, Chen Z, Jiang S (2012) Local morphology fitting active contour for automatic vascular segmentation. IEEE Trans Biomed Eng 59(2):464–473CrossRefGoogle Scholar
  30. 30.
    Zhang K, Song H, Zhang L (2010) Active contours driven by local image fitting energy. Pattern Recogn 43(4):1199–1206zbMATHCrossRefGoogle Scholar
  31. 31.
    Zhang J, Yu J, Tao D (2018) Local deep-feature alignment for unsupervised dimension reduction. IEEE Trans Image Process. Google Scholar
  32. 32.
    Yu J, Liu D, Tao D, Seah HS (2011) Complex object correspondence construction in 2D animation. IEEE Trans Image Process 20(11):3257–3269MathSciNetzbMATHCrossRefGoogle Scholar
  33. 33.
    Zhang K, Song H, Zhang L (2010) Active contours driven by local image fitting energy. Pattern Recogn 43(4):1199–1206zbMATHCrossRefGoogle Scholar
  34. 34.
    Zhang K, Zhang L, Lam KM et al (2015) A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans Cybern 46(2):546–557CrossRefGoogle Scholar
  35. 35.
    Goldstein T, Bresson X, Osher S (2010) Geometric applications of the split Bregman method: segmentation and surface reconstruction. J Sci Comput 45(1–3):272–293MathSciNetzbMATHCrossRefGoogle Scholar
  36. 36.
    Houhou N, Thiran J, Bresson X (2009) Fast texture segmentation based on semilocal region descriptor and active contour. Numer Math Theory Methods Appl 2(4):445–468MathSciNetzbMATHGoogle Scholar
  37. 37.
    Müller KR, Mika S, Rätsch G et al (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12(2):181–201CrossRefGoogle Scholar
  38. 38.
    Dhillon IS, Guan Y, Kulis B (2007) Weighted graph cuts without eigenvectors a multilevel approach. IEEE Trans Pattern Anal Mach Intell 29(11):1944–1957CrossRefGoogle Scholar
  39. 39.
    Wu KL, Yang MS (2002) Alternative c-means clustering algorithms. Pattern Recogn 35(10):2267–2278zbMATHCrossRefGoogle Scholar
  40. 40.
    Li C, Xu C, Gui C et al (2010) Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process 19(12):3243–3254MathSciNetzbMATHCrossRefGoogle Scholar
  41. 41.
    Booth S, Clausi D (2001) Image segmentation using MRI vertebral cross-sections. In: Canadian conference on electrical and computer engineering, 2001. IEEE, 2001, vol 2, pp 1303–1307Google Scholar
  42. 42.
    Wang T, Ji Z, Sun Q, Chen Q, Han S (2015) Image segmentation based on weighting boundary information via graphcut. J Vis Commun Image Represent 33(c):10–19CrossRefGoogle Scholar
  43. 43.
    Swain MJ, Ballard DH (1991) Color indexing. Int J Comput Vis 7:11–32CrossRefGoogle Scholar
  44. 44.
    Unnikrishnan R, Pantofaru C, Hebert M (2005) A measure for objective evaluation of image segmentation algorithms. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), vol 3, pp 34–41Google Scholar
  45. 45.
    Olveresa J, Navaa R, Moya-Alborb E, Escalante-Ramírez B, Brievab J, Cristóbal G, Vallejo E (2014) Texture descriptor approaches to level set segmentation in medical images. In: Proceedings of SPIE 9138, optics, photonics, and digital technologies for multimedia applications, vol III, 91380 J (15 May 2014).
  46. 46.
    Martin D, Fowlkes C, Malik J (2004) Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans Pattern Anal Mach Intell 26:530–549CrossRefGoogle Scholar
  47. 47.
    Peng B, Zhang L (2012) Evaluation of image segmentation quality by adaptive ground truth composition. In: 12th European conference on computer vision (ECCV). Lecture notes in computer science, vol 7574, pp 287–300Google Scholar
  48. 48.
    Liu W, Zhang H, Tao D, Wang Y, Lu K (2013) Large-scale paralleled sparse principal component analysis. Multimedia Tools Appl 75(3):1–13 Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.The School of Computer Science and TechnologyNanjing University of Science and TechnologyNanjingChina
  2. 2.China United Network Communications Corporation Jiangsu BranchNanjingChina

Personalised recommendations