Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Fully automatic figure-ground segmentation algorithm based on deep convolutional neural network and GrabCut

Figure-ground segmentation is used to extract the foreground from the background, where the foreground is usually defined as the region containing the most meaningful object of the image. In fact, the algorithms that take advantage of human–computer interaction often attain better performance and they are based on the ‘one-to-one’ model. In this study, the authors present a novel algorithm for figure-ground segmentation based on the GrabCut algorithm, which is a common segmentation algorithm that is user interactive. However, instead of a real user, they attempt to use a pre-trained deep convolutional neural network to interact with GrabCut for completing its job successfully. Weizmann's segmentation evaluation database is used as the test dataset and the results show that their algorithm works well for figure-ground segmentation. While the previous automatic segmentation algorithms are required to rank their segments empirically in order to find the position of the foreground after the segmentation, their algorithm is fully automatic.

References

    1. 1)
      • 18. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘ImageNet classification with deep convolutional neural networks’, Adv. Neural Inf. Process. Syst., 2012, 25, (2), pp. 11061114.
    2. 2)
      • 26. Ouyang, W., Luo, P., Zeng, X., et al: ‘DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection’, Eprint Arxiv, 2014.
    3. 3)
      • 14. Tang, M., Gorelick, L., Veksler, O., et al: ‘GrabCut in one cut’. ICCV, 2013, pp. 17691776.
    4. 4)
      • 2. Comaniciu, D., Meer, P.: ‘Mean shift: a robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603619.
    5. 5)
      • 28. Van Rijsbergen, C.J.: ‘Information retrieval’ (Department of Computer Science, University of Glasgow, Scotland, 1979, 2nd edn.).
    6. 6)
      • 29. Carreira, J., Sminchisescu, C.: ‘Constrained parametric min-cuts for automatic object segmentation’. Conf. Computer Vision Pattern Recognition, 2010, vol. 23, no. 3, pp. 32413248.
    7. 7)
      • 8. Rother, C., Kolmogorov, V., Blake, A.‘GrabCut’ interactive foreground extraction using iterated graph cuts’, ACM Trans. Graph., 2004, 23, (3), pp. 307312.
    8. 8)
      • 13. Hsiao, Y.M., Chang, L.W.: ‘Unsupervised figure-ground segmentation using edge detection and game-theoretical graph-cut approach’. IAPR Int. Conf. Machine Vision Applications, 2015.
    9. 9)
      • 24. Noh, H., Hong, S., Han, B.: ‘Learning deconvolution network for semantic segmentation’. IEEE Int. Conf. Comput. Vision, 2015, pp. 15201528.
    10. 10)
      • 11. Leibe, B., Schiele, B.: ‘Interleaved object categorization and segmentation’ (BMVA Press, County Durham, England, UK, 2003).
    11. 11)
      • 21. Girshick, R., Donahue, J., Darrell, T., et al: ‘Rich feature hierarchies for accurate object detection and semantic segmentation’, IEEE Conf. on Computer Vision and Pattern Recognition, June, 2014, pp. 580587.
    12. 12)
      • 30. Alpert, S., Galun, M., Basri, R., et al: ‘Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 34, (2), pp. 18.
    13. 13)
      • 3. Shi, J., Malik, J.: ‘Normalized cuts and image segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 888905.
    14. 14)
      • 17. Boykov, Y.Y., Jolly, M.P.: ‘Interactive graph cuts for optimal boundary and region segmentation of objects in ND images’. ICCV, 2001, vol. 1, pp. 105112.
    15. 15)
      • 16. Hernández-Vela, A., Reyes, M., Ponce, V., et al: ‘GrabCut-based human segmentation in video sequences’, Sensors, 2012, 12, (11), pp. 1537615393.
    16. 16)
      • 20. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, Eprint Arxiv, 2014.
    17. 17)
      • 15. Yang, W., Cai, J., Zheng, J., et al: ‘User-friendly interactive image segmentation through unified combinatorial user inputs’, IEEE Trans. Image Process., 2010, 19, (9), pp. 24702479.
    18. 18)
      • 7. Li, Y., Sun, J., Tang, C.K., et al: ‘Lazy snapping’, ACM Trans. Graph., 2004, 23, (3), pp. 303308.
    19. 19)
      • 27. ‘Segmentation evaluation database’. Available at http://www.wisdom.weizmann.ac.il/~vision/Seg_Evaluation_DB/index.html, accessed 20 May 2016.
    20. 20)
      • 32. Vedaldi, A., Lenc, K.: ‘MatConvNet – Convolutional Neural Networks for MATLAB’, Eprint Arxiv, 2014.
    21. 21)
      • 9. Riklinraviv, T., Kiryati, N., Sochen, N.: ‘Segmentation by level sets and symmetry’. IEEE Computer Society Conf. Computer Vision Pattern Recognition, 2006.
    22. 22)
      • 31. Carreira, J., Sminchisescu, C.: ‘CPMC: Automatic Object Segmentation Using Constrained Parametric MinCuts’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (7), pp. 13121328.
    23. 23)
      • 25. Chen, L.C., Papandreou, G., Kokkinos, I., et al: ‘Semantic image segmentation with deep convolutional nets and fully connected CRFs’, Int. Conf. on Learning Representations, May, 2015.
    24. 24)
      • 19. Sermanet, P., Eigen, D., Zhang, X., et al: ‘OverFeat: integrated recognition, localization and detection using convolutional networks’, Eprint Arxiv, 2013.
    25. 25)
      • 12. Levin, A., Weiss, Y.: ‘Learning to combine bottom-up and top-down segmentation’, Int. J. Comput. Vis., 2006, 81, (1), pp. 581594.
    26. 26)
      • 23. Long, J., Shelhamer, E., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’, Comput. Sci., 2014, 79, (10), pp. 13371342.
    27. 27)
      • 10. Borenstein, E., Ullman, S.: ‘Class-specific, top-down segmentation’ (ECCV, 2010), pp. 109124.
    28. 28)
      • 33. Sande, K.E.A.V.D., Uijlings, J.R.R., Gevers, T., et al: ‘Segmentation as selective search for object recognition’. IEEE International Conference on Computer Vision, 2011, pp. 18791886.
    29. 29)
      • 5. Galun, M., Sharon, E., Basri, R., et al: ‘Texture segmentation by multiscale aggregation of filter responses and shape elements’. Proc. Ninth IEEE Int. Conf. Computer Vision, 2003, vol. 2, pp. 716723.
    30. 30)
      • 6. Kadir, T., Brady, M.: ‘Unsupervised non-parametric region segmentation using level sets’. IEEE Int. Conf. Computer Vision, 2003, vol. 2, pp. 12671274.
    31. 31)
      • 22. Zhang, N., Donahue, J., Girshick, R., et al: ‘Part-based R-CNNs for fine-grained category detection’, Lec. Notes in Comput. Sci., 2014, 8689, pp. 834849.
    32. 32)
      • 1. Bagon, S., Boiman, O., Irani, M.: ‘What is a good image segment? A unified approach to segment extraction’ (ECCV, Springer Berlin Heidelberg, Germany, 2008), pp. 3044.
    33. 33)
      • 4. Malik, J., Belongie, S., Shi, J., et al: ‘Textons, contours and regions: cue integration in image segmentation’. Proc. Seventh IEEE Int. Conf. Computer Vision, 1999, vol. 2, pp. 918925.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0009
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0009
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address