Advertisement

Interactive Image Segmentation of Non-contiguous Classes Using Particle Competition and Cooperation

  • Fabricio BreveEmail author
  • Marcos G. Quiles
  • Liang Zhao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9155)

Abstract

Semi-supervised learning methods employ both labeled and unlabeled data in their training process. Therefore, they are commonly applied to interactive image processing tasks, where a human specialist may label a few pixels from the image and the algorithm would automatically propagate them to the remaining pixels, classifying the entire image. The particle competition and cooperation model is a recently proposed graph-based model, which was developed to perform semi-supervised classification. It employs teams of particles walking in a undirected and unweighed graph in order to classify data items corresponding to graph nodes. Each team represents a class problem, they try to dominate the unlabeled nodes in their neighborhood, at the same time that they try to avoid invasion from other teams. In this paper, the particle competition and cooperation model is applied to the task of interactive image segmentation. Image pixels are converted to graph nodes. Nodes are connected if they represent pixels with visual similarities. Labeled pixels generate particles that propagate their labels to the unlabeled pixels. Computer simulations are performed on some real-world images to show the effectiveness of the proposed approach. Images are correctly segmented in regions of interest, including non-contiguous regions.

Keywords

Semi-supervised learning Interactive image segmentation Machine learning Particle competition and cooperation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Artan, Y.: Interactive image segmentation using machine learning techniques. In: 2011 Canadian Conference on Computer and Robot Vision (CRV), pp. 264–269 (May 2011)Google Scholar
  2. 2.
    Artan, Y., Yetik, I.: Improved random walker algorithm for image segmentation. In: 2010 IEEE Southwest Symposium on Image Analysis Interpretation (SSIAI), pp. 89–92 (May 2010)Google Scholar
  3. 3.
    Belkin, M., Matveeva, I., Niyogi, P.: Regularization and semi-supervised learning on large graphs. In: Shawe-Taylor, J., Singer, Y. (eds.) COLT 2004. LNCS (LNAI), vol. 3120, pp. 624–638. Springer, Heidelberg (2004) CrossRefGoogle Scholar
  4. 4.
    Belkin, M., Niyogi, P., Sindhwani, V.: On manifold regularization. In: Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, AISTAT 2005, pp. 17–24. Society for Artificial Intelligence and Statistics, New Jersey (2005)Google Scholar
  5. 5.
    Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive Image Segmentation Using an Adaptive GMMRF Model. In: Pajdla, T., Matas, J.G. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 428–441. Springer, Heidelberg (2004). http://dx.doi.org/10.1007/978-3-540-24670-1_33
  6. 6.
    Blum, A., Chawla, S.: Learning from labeled and unlabeled data using graph mincuts. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 19–26. Morgan Kaufmann, San Francisco (2001)Google Scholar
  7. 7.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary amp; region segmentation of objects in n-d images. In: Proceedings of the Eighth IEEE International Conference on Computer Vision, ICCV 2001, vol. 1, pp. 105–112 (2001)Google Scholar
  8. 8.
    Breve, F.: Active semi-supervised learning using particle competition and cooperation in networks. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–6 (August 2013)Google Scholar
  9. 9.
    Breve, F., Zhao, L.: Particle competition and cooperation in networks for semi-supervised learning with concept drift. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–6 (June 2012)Google Scholar
  10. 10.
    Breve, F., Zhao, L.: Particle competition and cooperation to prevent error propagation from mislabeled data in semi-supervised learning. In: 2012 Brazilian Symposium on Neural Networks (SBRN), pp. 79–84 (October 2012)Google Scholar
  11. 11.
    Breve, F., Zhao, L.: Fuzzy community structure detection by particle competition and cooperation. Soft Computing 17(4), 659–673 (2013). http://dx.doi.org/10.1007/s00500-012-0924-3
  12. 12.
    Breve, F., Zhao, L., Quiles, M., Pedrycz, W., Liu, J.: Particle competition and cooperation for uncovering network overlap community structure. In: Liu, D., Zhang, H., Polycarpou, M., Alippi, C., He, H. (eds.) ISNN 2011, Part III. LNCS, vol. 6677, pp. 426–433. Springer, Heidelberg (2011). http://dx.doi.org/10.1007/978-3-642-21111-9_48
  13. 13.
    Breve, F., Zhao, L., Quiles, M., Pedrycz, W., Liu, J.: Particle competition and cooperation in networks for semi-supervised learning. IEEE Transactions on Knowledge and Data Engineering 24(9), 1686–1698 (2012)Google Scholar
  14. 14.
    Breve, F.A.: Combined active and semi-supervised learning using particle walking temporal dynamics. In: 2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence (BRICS-CCI CBIC), pp. 15–20 (Septemeber 2013)Google Scholar
  15. 15.
    Breve, F.A.: Query rules study on active semi-supervised learning using particle competition and cooperation. In: Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), pp. 134–140. São Carlos (2014)Google Scholar
  16. 16.
    Breve, F.A., Zhao, L.: Semi-supervised learning with concept drift using particle dynamics applied to network intrusion detection data. In: 2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence (BRICS-CCI CBIC), pp. 335–340 (September 2013)Google Scholar
  17. 17.
    Breve, F.A., Zhao, L., Quiles, M.G.: Semi-supervised learning from imperfect data through particle cooperation and competition. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (July 2010)Google Scholar
  18. 18.
    Breve, F.A., Zhao, L., Quiles, M.G.: Particle competition and cooperation for semi-supervised learning with label noise. Neurocomputing (2015) (article in Press)Google Scholar
  19. 19.
    Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-Supervised Learning. Adaptive Computation and Machine Learning. The MIT Press, Cambridge (2006)Google Scholar
  20. 20.
    Ding, L., Yilmaz, A.: Interactive image segmentation using probabilistic hypergraphs. Pattern Recognition 43(5), 1863–1873 (2010). http://www.sciencedirect.com/science/article/pii/S0031320309004440
  21. 21.
    Ducournau, A., Bretto, A.: Random walks in directed hypergraphs and application to semi-supervised image segmentation. Computer Vision and Image Understanding 120, 91–102 (2014). http://www.sciencedirect.com/science/article/pii/S1077314213002038
  22. 22.
    Friedman, J.H., Bentley, J.L., Finkel, R.A.: An algorithm for finding best matches in logarithmic expected time. ACM Trans. Math. Softw. 3(3), 209–226 (1977). http://doi.acm.org/10.1145/355744.355745
  23. 23.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice-Hall Inc., Upper Saddle River (2008)Google Scholar
  24. 24.
    Grady, L.: Random walks for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(11), 1768–1783 (2006)CrossRefGoogle Scholar
  25. 25.
    Joachims, T.: Transductive learning via spectral graph partitioning. In: Proceedings of International Conference on Machine Learning, pp. 290–297. AAAI Press (2003)Google Scholar
  26. 26.
    Li, J., Bioucas-Dias, J., Plaza, A.: Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE Transactions on Geoscience and Remote Sensing 48(11), 4085–4098 (2010)Google Scholar
  27. 27.
    Paiva, A., Tasdizen, T.: Fast semi-supervised image segmentation by novelty selection. In: 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 1054–1057 (March 2010)Google Scholar
  28. 28.
    Protiere, A., Sapiro, G.: Interactive image segmentation via adaptive weighted distances. IEEE Transactions on Image Processing 16(4), 1046–1057 (2007)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Rother, C., Kolmogorov, V., Blake, A.: grabcut: Interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004). http://doi.acm.org/10.1145/1015706.1015720
  30. 30.
    Shapiro, L., Stockman, G.: Computer Vision. Prentice Hall (2001)Google Scholar
  31. 31.
    Smith, A.R.: Color gamut transform pairs. In: ACM Siggraph Computer Graphics, vol. 12, pp. 12–19. ACM (1978)Google Scholar
  32. 32.
    Xu, J., Chen, X., Huang, X.: Interactive image segmentation by semi-supervised learning ensemble. In: International Symposium on Knowledge Acquisition and Modeling, KAM 2008, pp. 645–648 (December 2008)Google Scholar
  33. 33.
    Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: Advances in Neural Information Processing Systems, vol. 16, pp. 321–328. MIT Press (2004). http://www.kyb.tuebingen.mpg.de/bs/people/weston/localglobal.pdf
  34. 34.
    Zhu, X.: Semi-supervised learning literature survey. Tech. Rep. 1530, Computer Sciences, University of Wisconsin-Madison (2005)Google Scholar
  35. 35.
    Zhu, X., Ghahramani, Z., Lafferty, J.: Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of the Twentieth International Conference on Machine Learning, pp. 912–919 (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.São Paulo State University (UNESP)Rio ClaroBrazil
  2. 2.Federal University of São Paulo (Unifesp)Rio ClaroBrazil
  3. 3.University of São Paulo (USP)Rio ClaroBrazil

Personalised recommendations