http://iet.metastore.ingenta.com
1887

Image segmentation fusion using weakly supervised trace-norm multi-task learning method

Image segmentation fusion using weakly supervised trace-norm multi-task learning method

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Image Processing — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

In this study, the authors propose a new method to fuse multiple segmentations generated by different methods or same methods with different parameters. The proposed method has several contributions. First, they convert the image segmentation fusion problem into a weakly supervised learning problem. Thus, the information of superpixels can be used to guide the fusion process. Second, they treat the multiple segmentations as multiple closely related tasks and utilise multi-task learning method to evaluate the reliability of the segmentations. Third, they design a strategy to ensemble the evaluated segmentation maps to obtain the final segmentation. The experiment on the benchmark dataset MSRC demonstrates the superior performance of the proposed method on image foreground and background segmentations.

References

    1. 1)
      • Y.Y. Boykov , M.-P. Jolly .
        1. Boykov, Y.Y., Jolly, M.-P.: ‘Interactive graph cuts for optimal boundary & region segmentation of objects in Nd images’. Proc. Int. Conf. Int. Conf. Computer Vision, 2001, pp. 105112.
        . Proc. Int. Conf. Int. Conf. Computer Vision , 105 - 112
    2. 2)
      • J. Shi , J. Malik .
        2. Shi, J., Malik, J.: ‘Normalized cuts and image segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 888905.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 8 , 888 - 905
    3. 3)
      • T. Cour , F. Benezit , J. Shi .
        3. Cour, T., Benezit, F., Shi, J.: ‘Spectral segmentation with multiscale graph decomposition’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2005, pp. 11241131.
        . Proc. Int. Conf. Computer Vision and Pattern Recognition , 1124 - 1131
    4. 4)
      • S. Ray , R.H. Turi .
        4. Ray, S., Turi, R.H.: ‘Determination of number of clusters in K-means clustering and application in colour image segmentation’. Proc. Int. Conf. Advances in Pattern Recognition and Digital Techniques, 1999, pp. 137143.
        . Proc. Int. Conf. Advances in Pattern Recognition and Digital Techniques , 137 - 143
    5. 5)
      • D. Comaniciu , P. Meer .
        5. Comaniciu, D., Meer, P.: ‘Mean shift: a robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603619.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 5 , 603 - 619
    6. 6)
      • L. Gupta , T. Sortrakul .
        6. Gupta, L., Sortrakul, T.: ‘A Gaussian-mixture-based image segmentation algorithm’, Pattern Recognit., 1998, 31, (3), pp. 315325.
        . Pattern Recognit. , 3 , 315 - 325
    7. 7)
      • N. Senthilkumaran , R. Rajesh .
        7. Senthilkumaran, N., Rajesh, R.: ‘Edge detection techniques for image segmentation – a survey of soft computing approaches’, Int. J. Recent Trends Eng., 2009, 1, (2), pp. 250254.
        . Int. J. Recent Trends Eng. , 2 , 250 - 254
    8. 8)
      • S. Konishi , A.L. Yuille , J.M. Coughlan .
        8. Konishi, S., Yuille, A.L., Coughlan, J.M., et al: ‘Statistical edge detection: learning and evaluating edge cues’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (1), pp. 5774.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 1 , 57 - 74
    9. 9)
      • H. Kim , J.J. Thiagarajan , P.-T. Bremer .
        9. Kim, H., Thiagarajan, J.J., Bremer, P.-T.: ‘Image segmentation using consensus from hierarchical segmentation ensembles’. 2014 IEEE Int. Conf. Proc. Int. Conf. Image Processing (ICIP), 2014, pp. 32723276.
        . 2014 IEEE Int. Conf. Proc. Int. Conf. Image Processing (ICIP) , 3272 - 3276
    10. 10)
      • Q. Ge , E. Lobaton .
        10. Ge, Q., Lobaton, E.: ‘Consensus-based image segmentation via topological persistence’. Proc. Int. Conf. Computer Vision and Pattern Recognition Workshops, 2016, pp. 95102.
        . Proc. Int. Conf. Computer Vision and Pattern Recognition Workshops , 95 - 102
    11. 11)
      • L. Franek , D.D. Abdala , S. Vega-Pons .
        11. Franek, L., Abdala, D.D., Vega-Pons, S., et al: ‘Image segmentation fusion using general ensemble clustering methods’. Proc. Int. Conf. Asian Conf. Computer Vision, 2010, pp. 373384.
        . Proc. Int. Conf. Asian Conf. Computer Vision , 373 - 384
    12. 12)
      • A. Alush , J. Goldberger .
        12. Alush, A., Goldberger, J.: ‘Ensemble segmentation using efficient integer linear programming’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (10), pp. 19661977.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 10 , 1966 - 1977
    13. 13)
      • M. Ozay , F.T.Y. Vural , S.R. Kulkarni .
        13. Ozay, M., Vural, F.T.Y., Kulkarni, S.R., et al: ‘Fusion of image segmentation algorithms using consensus clustering’. 2013 20th IEEE Int. Conf. Proc. Int. Conf. Image Processing (ICIP), 2013, pp. 40494053.
        . 2013 20th IEEE Int. Conf. Proc. Int. Conf. Image Processing (ICIP) , 4049 - 4053
    14. 14)
      • F. Nielsen , R. Nock .
        14. Nielsen, F., Nock, R.: ‘Consensus region merging for image segmentation’. 2013 Second IAPR Asian Conf. Proc. Int. Conf. Pattern Recognition (ACPR), 2013, pp. 325329.
        . 2013 Second IAPR Asian Conf. Proc. Int. Conf. Pattern Recognition (ACPR) , 325 - 329
    15. 15)
      • L. Khelifi , M. Mignotte .
        15. Khelifi, L., Mignotte, M.: ‘A novel fusion approach based on the global consistency criterion to fusing multiple segmentations’, IEEE Trans. Syst. Man Cybern. Syst., 2017, 47, (9), pp. 24892502.
        . IEEE Trans. Syst. Man Cybern. Syst. , 9 , 2489 - 2502
    16. 16)
      • L. Khelifi , M. Mignotte .
        16. Khelifi, L., Mignotte, M.: ‘A multi-objective decision making approach for solving the image segmentation fusion problem’, IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc., 2017, 26, (8), p. 3831.
        . IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. , 8 , 3831
    17. 17)
      • V. Singh , L. Mukherjee , J. Peng .
        17. Singh, V., Mukherjee, L., Peng, J., et al: ‘Ensemble clustering using semidefinite programming with applications’, Mach. Learn., 2010, 79, (1), pp. 177200.
        . Mach. Learn. , 1 , 177 - 200
    18. 18)
      • S.R. Rao , H. Mobahi , A.Y. Yang .
        18. Rao, S.R., Mobahi, H., Yang, A.Y., et al: ‘Natural image segmentation with adaptive texture and boundary encoding’. Proc. Int. Conf. Asian Conf. Computer Vision, 2009, pp. 135146.
        . Proc. Int. Conf. Asian Conf. Computer Vision , 135 - 146
    19. 19)
      • C. Lee , W.-D. Jang , J.-Y. Sim .
        19. Lee, C., Jang, W.-D., Sim, J.-Y., et al: ‘Multiple random walkers and their application to image cosegmentation’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2015, pp. 38373845.
        . Proc. Int. Conf. Computer Vision and Pattern Recognition , 3837 - 3845
    20. 20)
      • H. Fu , D. Xu , B. Zhang .
        20. Fu, H., Xu, D., Zhang, B., et al: ‘Object-based multiple foreground video co-segmentation via multi-state selection graph’, IEEE Trans. Image Process., 2015, 24, (11), pp. 34153424.
        . IEEE Trans. Image Process. , 11 , 3415 - 3424
    21. 21)
      • Q. Wang , Y. Yuan , P. Yan .
        21. Wang, Q., Yuan, Y., Yan, P., et al: ‘Saliency detection by multiple-instance learning’, IEEE Trans. Cybern., 2013, 43, (2), pp. 660672.
        . IEEE Trans. Cybern. , 2 , 660 - 672
    22. 22)
      • Q. Wang , Y. Yuan , P. Yan .
        22. Wang, Q., Yuan, Y., Yan, P.: ‘Visual saliency by selective contrast’, IEEE Trans. Circuits Syst. Video Technol., 2013, 23, (7), pp. 11501155.
        . IEEE Trans. Circuits Syst. Video Technol. , 7 , 1150 - 1155
    23. 23)
      • E. Shelhamer , J. Long , T. Darrell .
        23. Shelhamer, E., Long, J., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2017, 39, (4), pp. 640651.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 4 , 640 - 651
    24. 24)
      • D. Lin , J. Dai , J. Jia .
        24. Lin, D., Dai, J., Jia, J., et al: ‘Scribblesup: scribble-supervised convolutional networks for semantic segmentation’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2016, pp. 31593167.
        . Proc. Int. Conf. Computer Vision and Pattern Recognition , 3159 - 3167
    25. 25)
      • G. Lin , C. Shen , D.H.A. Van .
        25. Lin, G., Shen, C., Van, D.H.A., et al: ‘Exploring context with deep structured models for semantic segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2017, (99), p. 1, doi: 10.1109/TPAMI.2017.2708714.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 99 , 1
    26. 26)
      • X. Liang , L. Zhu , D.-S. Huang .
        26. Liang, X., Zhu, L., Huang, D.-S.: ‘Optimization of gene set annotations using robust trace-norm multitask learning’, IEEE/ACM Trans. Comput. Biol. Bioinf., 2017, doi: 10.1109/TCBB.2017.2690427.
        . IEEE/ACM Trans. Comput. Biol. Bioinf.
    27. 27)
      • J. Liu , S. Ji , J. Ye .
        27. Liu, J., Ji, S., Ye, J.: ‘Multi-task feature learning via efficient L 2, 1-norm minimization’. Proc. Int. Conf. Proc. 25 Conf. Uncertainty in Artificial Intelligence, 2009, pp. 339348.
        . Proc. Int. Conf. Proc. 25 Conf. Uncertainty in Artificial Intelligence , 339 - 348
    28. 28)
      • T.K. Pong , P. Tseng , S. Ji .
        28. Pong, T.K., Tseng, P., Ji, S., et al: ‘Trace norm regularization: reformulations, algorithms, and multi-task learning’, SIAM J. Optim., 2010, 20, (6), pp. 34653489.
        . SIAM J. Optim. , 6 , 3465 - 3489
    29. 29)
      • L. Jacob , J.-P. Vert , F.R. Bach .
        29. Jacob, L., Vert, J.-P., Bach, F.R.: ‘Clustered multi-task learning: a convex formulation’. Proc. Int. Conf. Advances in Neural Information Processing Systems, 2009, pp. 745752.
        . Proc. Int. Conf. Advances in Neural Information Processing Systems , 745 - 752
    30. 30)
      • R. Achanta , A. Shaji , K. Smith .
        30. Achanta, R., Shaji, A., Smith, K., et al: ‘SLIC superpixels compared to state-of-the-art superpixel methods’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (11), pp. 22742282.
        . IEEE Trans. Pattern Anal. Mach. Intell. , 11 , 2274 - 2282
    31. 31)
      • H. Jiang , J. Wang , Z. Yuan .
        31. Jiang, H., Wang, J., Yuan, Z., et al: ‘Salient object detection: a discriminative regional feature integration approach’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2013, pp. 20832090.
        . Proc. Int. Conf. Computer Vision and Pattern Recognition , 2083 - 2090
    32. 32)
      • S. Ji , J. Ye .
        32. Ji, S., Ye, J.: ‘An accelerated gradient method for trace norm minimization’. Proc. Int. Conf. Machine Learning, 2009, pp. 457464.
        . Proc. Int. Conf. Machine Learning , 457 - 464
    33. 33)
      • Q. Zhang , J. Zhou , Y. Wang .
        33. Zhang, Q., Zhou, J., Wang, Y., et al: ‘Image cosegmentation via multi-task learning’. Proc. Int. Conf. BMVC, 2014.
        . Proc. Int. Conf. BMVC
    34. 34)
      • M. Rubinstein , A. Joulin , J. Kopf .
        34. Rubinstein, M., Joulin, A., Kopf, J., et al: ‘Unsupervised joint object discovery and segmentation in Internet images’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2013, pp. 19391946.
        . Proc. Int. Conf. Computer Vision and Pattern Recognition , 1939 - 1946
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.1061
Loading

Related content

content/journals/10.1049/iet-ipr.2017.1061
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address