Skip to main content
SpringerLink
Log in

Image Co-segmentation by Co-diffusion

  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

Abstract

In this paper, a co-segmentation algorithm based on 3D heat diffusion named co-diffusion is proposed. The image set is considered as a metal cuboid, and the K heat sources with constant temperature, which maximize the sum of the temperature of the system under anisotropic heat diffusion, are found to cluster the image set. The co-diffusion co-segmentation is an intuitive extension of the diffusion segmentation in Kim et al. (Proceedings of ICCV, 2011) while the performance is greatly improved. Comparatively, the proposed algorithm advances in the following three aspects: (1) The proposed algorithm can obtain better optimization because the heat diffusion is directly solved in 3D image set space, while the algorithm in Kim et al. (2011) deals with many independent 2D heat diffusions and solves the optimization by approximate belief propagation. (2) The marginal gain of every candidate heat source is globally determined in the image set, which can effectively compensate the wrong segmentations caused by the locality of the 2D image diffusion (Kim et al. 2011). (3) The K heat sources are chosen in image set while the algorithm (Kim et al. 2011) appoints mandatory K heat sources to each image in set, which will inevitably cause wrong segmentations for some images. The superiority of the proposed co-diffusion segmentation method is examined and demonstrated through a large number of experiments by using some typical datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. D. Batra, A. Kowdle, D. Parikh, J. Luo, T. Chen, iCoseg: interactive co-segmentation with intelligent scribble guidance, in Proceedings of CVPR, pp. 3169–3176 (2010)

  2. Y. Boykov, O. Veksler, R. Zabih, Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal Mach. Intell. 23(11), 1222–1239 (2001)

    Article  Google Scholar 

  3. A. Bruhn, J. Weickert, C. Schnörr, Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 61(3), 211–231 (2005)

    Article  Google Scholar 

  4. K.-Y. Chang, T.-L. Liu, S.-H. Lai, From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model, in Proceedings of CVPR, pp. 2129–2136 (2011)

  5. J. Dai, Y.N. Wu, J. Zhou, S.C. Zhu, Cosegmentation and cosketch by unsupervised learning, in Proceedings of ICCV, pp. 1305–1312 (2013)

  6. L. Grady, Random walks for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 28(11), 1768–1783 (2006)

    Article  Google Scholar 

  7. Y. Guo, A. Sengur, A novel color image segmentation approach based on neutrosophic set and modified fuzzy c-means. Circuits, Systems and Signal Processing 32(4), 1699–1723 (2013)

    Article  MathSciNet  Google Scholar 

  8. S. Han, W. Tao, X. Wu, Texture segmentation using independent-scale component-wise Riemannian-covariance Gaussian mixture model in KL measure based multi-scale nonlinear structure tensor space. Pattern Recognit. 44(3), 503–518 (2011)

    Article  MATH  Google Scholar 

  9. D.S. Hochbaum, V. Singh, An efficient algorithm for cosegmentation, in Proceedings of ICCV, pp. 269–276 (2009)

  10. W. Hu, H. Wang, Z. Qiu, C. Nie, L. Yan, B. Du, An event detection method for social networks based on hybrid link prediction and quantum swarm intelligent. World Wide Web. Publish online

  11. W. Hu, H. Wang, Z. Qiu, C. Nie, L. Yan. A quantum particle swarm optimization driven urban traffic light scheduling model. Neural Computing and Applications. Publish online

  12. W. Hu, H. Wang, Z. Min, A storage allocation algorithm for outbound containers based on the outer–inner cellular automaton. Inf. Sci. 281, 147–171 (2014)

    Article  MathSciNet  Google Scholar 

  13. A. Joulin, F. Bach, J. Ponce, Discriminative clustering for image co-segmentation, in Proceedings of CVPR, pp. 1943–1950 (2010)

  14. A. Joulin, F. Bach, J. Ponce, Multi-class cosegmentation, in Proceedings of CVPR, pp. 542–549 (2012)

  15. E. Kim, H. Li, X. Huang, A hierarchical image clustering cosegmentation framework, in Proceedings of CVPR, pp. 686–693 (2012)

  16. G. Kim, E.P. Xing, On multiple foreground cosegmentation, in Proceedings of CVPR, pp. 837–844 (2012)

  17. G. Kim, E.P. Xing, L. Fei-Fei, T. Kanade, Distributed cosegmentation vis submodular optimization on anisotropic diffusion, in Proceedings of ICCV, pp. 169–176 (2011)

  18. A. Krause, C. Guestrin, Beyond Convexity: Submodularity in Machine Learning (ICML Tutorials, New York, 2008)

    Google Scholar 

  19. A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dickinson, K. Siddiqi, Turbopixels: fast superpixels using geometric flows. IEEE Trans. Pattern Anal. Mach. Intell. 31(12), 2290–2297 (2009)

    Article  Google Scholar 

  20. H. Li, F. Meng, K.N. Ngan, Co-salient object detection from multiple images. IEEE Trans. Multimedia 15(8), 1896–1909 (2013)

    Article  Google Scholar 

  21. H. Li, F. Meng, Q. Wu, B. Luo, Unsupervised multiclass region cosegmentation via ensemble clustering and energy minimization. IEEE Trans. Circuits Syst. Video Technol. 24(5), 789–801 (2014)

    Article  Google Scholar 

  22. K. Li, W. Tao, Adaptive optimal shape prior for easy interactive object segmentation. IEEE Trans. Multimedia 17(7), 994–1005 (2015)

    Article  Google Scholar 

  23. K. Li, W. Tao, Unsupervised co-segmentation for indefinite number of common foreground objects. IEEE Trans. Image Process. 25(4), 1898–1909 (2016)

    Article  MathSciNet  Google Scholar 

  24. S. Liu, S. Yan, C. Xu, H. Lu, Weakly-supervised graph propagation towards collective image parsing. IEEE Trans. Multimedia 14(2), 361–373 (2012)

    Article  Google Scholar 

  25. L. Liu, W. Tao, H. Liu, Complementary saliency driven co-segmentation with region searching and Hierarchical constraint. Inf. Sci. 372, 72–83 (2016)

    Article  Google Scholar 

  26. L. Liu, W. Tao, Image segmentation by iterative optimization of multiphase multiple piecewise constant model and Four-Color relabeling. Pattern Recognit. 44(12), 2819–2833 (2011)

    Article  MATH  Google Scholar 

  27. F. Meng, H. Li, G. Liu, K.N. Ngan, Object co-segmentation based on shortest path algorithm and saliency model. IEEE Trans. Multimedia 14(5), 1429–1441 (2012)

    Article  Google Scholar 

  28. F. Meng, H. Li, K.N. Ngan, L. Zeng, Q. Wu, Feature adaptive co-segmentation by complexity awareness. IEEE Trans. Image Process. 22(12), 4809–4824 (2013)

    Article  MathSciNet  Google Scholar 

  29. L. Mukherjee, V. Singh, C.R. Dyer, Half-integrality based algorithms for cosegmentation of images, in Proceedings of CVPR, pp. 2028–2035 (2009)

  30. L. Mukherjee, V. Singh, J. Peng, Scale invariant cosegmentation for image groups, in Proceedings of CVPR, pp. 1881–1888 (2011)

  31. G.L. Nemhauser, L.A. Wolsey, M.L. Fisher, An analysis of approximations for maximizing submodular set functions. Math. Programm. 14, 265–294 (1978)

    Article  MathSciNet  MATH  Google Scholar 

  32. N. Otsu, A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)

    Article  Google Scholar 

  33. C. Rother, T. Minka, A. Blake, V. Kolmogorov, Cosegmentation of image pairs by histogram matching incorporating a global constraint into mrfs, in Proceedings of CVPR, pp. 993–1000 (2006)

  34. M. Rubinstein, A. Joulin, J. Kopf, C. Liu, Unsupervised joint object discovery and segmentation in internet images, in Proceedings of CVPR, pp. 1939–1946 (2013)

  35. J. Shi, J. Malik, Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)

    Article  Google Scholar 

  36. H. Song, Active contours driven by regularised gradient flux flows for image segmentation. Electron. Lett. 50(14), 992–994 (2014)

    Article  Google Scholar 

  37. M. Srivastava, S.K. Singh, P.K. Panigrahi, A Semi-Automated Statistical Algorithm for Object Separation. Circuits Syst. Signal Process. 32(6), 3059–3078 (2013)

    Article  MathSciNet  Google Scholar 

  38. Y. Tang, W. Mu, X. Zhang, Y. Yang, Modified fuzzy linear discriminant analysis for threshold selection. Circuits Syst. Signal Process. 32(2), 711–726 (2013)

    Article  MathSciNet  Google Scholar 

  39. W. Tao, H. Jin, Y. Zhang, Color image segmentation based on mean shift and normalized cuts. IEEE Trans. Syst. Man Cybern. Part B Cybern. 37(5), 1382–1389 (2007)

    Article  Google Scholar 

  40. W. Tao, K. Li, K. Sun, Sacoseg: object cosegmentation by shape conformability. IEEE Trans. Image Process. 24(3), 943–955 (2015)

    Article  MathSciNet  Google Scholar 

  41. W. Tao, H. Jin, Ship infrared object segmentation based on mean shift filtering and graph spectral clustering. J. Infrared Millim. Waves 26(1), 61–64 (2007)

    Google Scholar 

  42. A. Toshev, J. Shi, K. Daniilidis, Image matching via saliency region correspondences, in Proceedings of CVPR, pp. 1–8 (2007)

  43. S. Vicente, V. Kolmogorov, C. Rother, Cosegmentation revisited: models and optimization, in Proceedings of ECCV, pp. 465–479 (2010)

  44. S. Vicente, C. Rother, V. Kolmogorov, Object cosegmentation, in Proceedings of CVPR, pp. 2217–2224 (2011)

  45. F. Wang, Q. Huang, M. Ovsjanikov, L.J. Guibas, Unsupervised multi-class joint image segmentation, in Proceedings of CVPR, pp. 3143–3149 (2014)

  46. J. Weickert, Anisotropic Diffusion in Image Processing. ECMI Series (Teubner-Verlag, Stuttgart, 1998)

    MATH  Google Scholar 

  47. J. Winn, A. Criminisi, T. Minka, Object categorization by learned universal visual dictionary, in Proceedings of ICCV, pp. 1800–1807 (2005)

  48. C. Zhang, J. Liu, Q. Tian, C. Xu, H. Lu, S. Ma, Image classification by non-negative sparse coding, low-rank and sparse decomposition, in Proceedings of CVPR, pp. 1673-1680 (2011)

  49. J. Zhang, J. Zheng, J. Cai. A diffusion approach to seeded image segmentation, in Proceedings of CVPR, pp. 2125–2132 (2010)

  50. K. Zhang, L. Zhang, K.M. Lam, D. Zhang, A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans. Cybern. 46(2), 546–557 (2016)

    Article  Google Scholar 

  51. X. Zhu, Z. Ghahramani, J. Lafferty, Semi-supervised learning using Gaussian fields and harmonic functions. ICML, pp. 912–919 (2003)

Download references

Acknowledgements

This work is supported by National Natural Science Foundation of China (Grants 61371140 and 61305044) and in part by Natural Science Foundation of Hubei Province (2015CFA062) and 2015BAA133. This work is conducted while Kunqian Li is working at the Huazhong University of Science and Technology.

Author information

Authors and Affiliations

  1. School of Biomedical Engineering, South-Central University for Nationalities, Wuhan, 430074, China

    Liman Liu, Kunqian Li & Xiangli Liao

Authors
  1. Liman Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kunqian Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiangli Liao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kunqian Li.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, L., Li, K. & Liao, X. Image Co-segmentation by Co-diffusion. Circuits Syst Signal Process 36, 4423–4440 (2017). https://doi.org/10.1007/s00034-017-0518-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-017-0518-5

Keywords

Search

Navigation