Parallel Accelerated Matting Method Based on Local Learning

  • Xiaoqiang LiEmail author
  • Qing Cui
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10111)


To pursue effective and fast matting method is of great importance in digital image editing. This paper proposes a scheme to accelerate learning based digital matting and implement it on modern GPU in parallel, which involves learning stage and solving stage. Firstly, we present GPU-based method to accelerate the pixel-wise learning stage. Then, trimap skeleton based algorithm is proposed to divide the image into blocks and process blocks in parallel to speed up the solving stage. Experimental results demonstrated that the proposed scheme achieves a maximal 12+ speedup over previous serial methods without degrading segmentation precision.


Neighboring Pixel Horizontal Segment Critical Node Local Learning Serial Version 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Zheng, Y., Kambhamettu, C.: Learning based digital matting. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 889–896. IEEE (2009)Google Scholar
  2. 2.
    Zhu, J., Lu, G., Zhang, D.: Growmatting: a GPU-based real-time interactive method for image matting. In: 2010 25th International Conference of Image and Vision Computing New Zealand (IVCNZ), pp. 1–8. IEEE (2010)Google Scholar
  3. 3.
    Xiao, C., Liu, M., Xiao, D., Dong, Z., Ma, K.L.: Fast closed-form matting using a hierarchical data structure. IEEE Trans. Circ. Syst. Video Technol. 24, 49–62 (2014)CrossRefGoogle Scholar
  4. 4.
    Sun, X., Wang, Z., Chen, G.: Parallel active contour with lattice boltzmann scheme on modern GPU. In: 2012 19th IEEE International Conference on Image Processing (ICIP), pp. 1709–1712. IEEE (2012)Google Scholar
  5. 5.
    Zhang, Q., Xiao, C.: Cloud detection of RGB color aerial photographs by progressive refinement scheme. IEEE Trans. Geosci. Remote Sens. 52, 7264–7275 (2014)CrossRefGoogle Scholar
  6. 6.
    Zhao, M., Fu, C.W., Cai, J., Cham, T.J.: Real-time and temporal-coherent foreground extraction with commodity RGBD camera. IEEE J. Sel. Top. Sign. Process. 9, 449–461 (2015)CrossRefGoogle Scholar
  7. 7.
    He, K., Sun, J., Tang, X.: Fast matting using large kernel matting laplacian matrices. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2165–2172. IEEE (2010)Google Scholar
  8. 8.
    Zhang, Z., Zhu, Q., Xie, Y.: Learning based alpha matting using support vector regression. In: 2012 19th IEEE International Conference on Image Processing (ICIP), pp. 2109–2112. IEEE (2012)Google Scholar
  9. 9.
    Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30, 228–242 (2008)CrossRefGoogle Scholar
  10. 10.
    Guo, Z., Hall, R.W.: Parallel thinning with two-subiteration algorithms. Commun. ACM 32, 359–373 (1989)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Ramer, U.: An iterative procedure for the polygonal approximation of plane curves. Comput. Graph. Image Process. 1, 244–256 (1972)CrossRefGoogle Scholar
  12. 12.
    Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 1826–1833. IEEE (2009)Google Scholar
  13. 13.
    UMFPACK: Suitesparse 4.4.6. (2015).
  14. 14.
    LDLT: Eigen 3.2.4. (2015).

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of Computer Engineering and ScienceShanghai UniversityShanghaiChina

Personalised recommendations