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

access icon free Saliency-based initialisation of Gaussian mixture models for fully-automatic object segmentation

The conventional object segmentation methods often degrade their performance due to the requirement of user interaction and/or the incomplete colour appearance models. In this Letter, the authors propose a novel design method of a colour appearance model for accurate and fully-automatic object segmentation by using saliency maps. The authors initialise the Gaussian mixture models (GMMs) to describe the colour appearance of the foreground objects and the background, respectively, where the mean vectors, covariance matrices, and mixing coefficients are updated adaptively such that more salient pixels have larger weights to update the GMM for the foreground objects while less salient pixels have larger weights to update the GMM for the background, respectively. Experiments are performed on MSRC, iCoseg, and PASCAL datasets and we show that the proposed method outperforms the existing methods quantitatively and qualitatively.

References

    1. 1)
      • 10. Rubio, J.C., Serrat, J., Lopez, A., et al: ‘Unsupervised co-segmentation through region matching’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 749756.
    2. 2)
      • 8. Rubinstein, M., Joulin, A., Kopf, J., et al: ‘Unsupervised joint object discovery and segmentation in internet images’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 19391946.
    3. 3)
      • 17. Vicente, S., Rother, C., Kolmogorov, V.: ‘Object cosegmentation’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2011, pp. 22172224.
    4. 4)
      • 5. Li, X., Hao, J., Shang, M., et al: ‘Saliency segmentation and foreground extraction of underwater image based on localization’. IEEE OCEANS 2016-Shanghai, 2016, pp. 14.
    5. 5)
      • 7. Kruthiventi, S.S., Gudisa, V., Dholakiya, J.H., et al: ‘Saliency unified: a deep architecture for simultaneous eye fixation prediction and salient object segmentation’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 57815790.
    6. 6)
      • 4. Mehrani, P., Veksier, O.: ‘Saliency segmentation based on learning and graph cut refinement’. British Machine Vision Conf., 2010, pp. 112.
    7. 7)
      • 11. [Online] Available at: https://www.microsoft.com/en-us/research/project /image-understanding/.
    8. 8)
    9. 9)
      • 15. [Online] Available at: http://vision.csd.uwo.ca/code/.
    10. 10)
      • 12. Batra, D., Kowdle, A., Parikh, D., et al: ‘Icoseg: interactive co-segmentation with intelligent scribble guidance’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 31693176.
    11. 11)
      • 6. Christopher, M.B.: ‘Pattern recognition and machine learning’ (Springer, New York, NY, USA, 2006), pp. 423455.
    12. 12)
    13. 13)
      • 18. Shi, R., Ngan, K.N., Li, S.: ‘Jaccard index compensation for object segmentation evaluation’. Proc. IEEE Int. Conf. on Image Processing (ICIP), 2014, pp. 44574461.
    14. 14)
    15. 15)
    16. 16)
      • 14. Zhu, W., Liang, S., Wei, Y., et al: ‘Saliency optimization from robust background detection’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 28142821.
    17. 17)
    18. 18)
      • 16. Margolin, R., Zelnik-Manor, L., Tal, A.: ‘How to evaluate foreground maps?’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 248255.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.3877
Loading

Related content

content/journals/10.1049/el.2017.3877
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address