Skip to main content

Natural Image Matting Based on Neighbor Embedding

  • Conference paper
Computer Vision/Computer Graphics Collaboration Techniques (MIRAGE 2007)

Abstract

In this paper, an automatic technique for natural image matting is proposed. We use visual characteristics of the background and foreground regions for matting. Through the Locally Linear Embedding (LLE) of high-dimensional features, we estimate foreground and background color of unknown pixels. We use gradient information and a hierarchical model to enhance the proposed matting technique. Instead of a user interaction for tri-map generation, we propose an automatic technique that obtains a tri-map using a multi-view camera. A reliability map for the depth of a scene facilitates the generation of a tri-map. It is proven that feature sets obtained from training images can be applied to similar images or video frames.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Wren, C., et al.: Pfinder: Real-Time Tracking of the Human Body. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7), 780–785 (1997)

    Article  Google Scholar 

  2. Lee, S.-Y., et al.: Active Segmentation for Immersive Live Avatar. Electronics Letters 40, 1257–1258 (2004)

    Article  Google Scholar 

  3. Gvili, R., et al.: Depth Keying. In: Proceedings of SPIE Electronic Imaging, pp. 564–574 (2003)

    Google Scholar 

  4. McGuire, M., et al.: Defocus Video Matting. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2005) 24, 567–576 (2005)

    Article  Google Scholar 

  5. Chuang, Y.-Y., et al.: A Bayesian Approach to Digital Matting. In: Proceedings of CVPR2001, Dec. 2001, pp. 264–271 (2001)

    Google Scholar 

  6. Mitsunaga, T., Yokoyama, T., Totsuka, T.: Autokey: Human Assisted Key Extraction. In: Proceedings of ACM SIGGRAPH 95, Aug. 1995, pp. 265–272. ACM Press, New York (1995)

    Chapter  Google Scholar 

  7. Ruzon, M., Tomasi, C.: Alpha Estimation in Natural Images. In: Proceedings of CVPR2000, Jun. 2000, pp. 18–25 (2000)

    Google Scholar 

  8. Sun, J., et al.: Poisson Matting. ACM Transactions on Graphics (Proceedings of the SIGGRAPH 2004) 23(3), 315–321 (2004)

    Article  Google Scholar 

  9. Chuang, Y.-Y., et al.: Video Matting of Complex Scenes. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2002) 21(3), 243–248 (2002)

    Article  Google Scholar 

  10. Roweis, S.T., Saul, L.K.: Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science 290(5500), 2323–2326 (2000)

    Article  Google Scholar 

  11. Lawson, C.L., Hanson, R.J.: Solving Least Squares Problems. Prentice-Hall, Englewood Cliffs (1974)

    MATH  Google Scholar 

  12. Burt, P.J.: The Laplacian Pyramid as a Compact Image Code. IEEE Transactions on Communications 31(4), 532–540 (1983)

    Article  Google Scholar 

  13. Park, S.Y., Subbarao, M.: An Accurate and Fast Point-to-Plane Registration Technique. Pattern Recognition Letter 24(16), 2967–2976 (2003)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

André Gagalowicz Wilfried Philips

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Won, K.H., Park, SY., Jung, S.K. (2007). Natural Image Matting Based on Neighbor Embedding. In: Gagalowicz, A., Philips, W. (eds) Computer Vision/Computer Graphics Collaboration Techniques. MIRAGE 2007. Lecture Notes in Computer Science, vol 4418. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71457-6_41

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-71457-6_41

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-71456-9

  • Online ISBN: 978-3-540-71457-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics