Advertisement

The Visual Computer

, Volume 22, Issue 9–11, pp 661–670 | Cite as

Object-based vectorization for interactive image editing

Special Issue Paper

Abstract

We present a technique for creating an editable vector graphic from an object in a raster image. Object selection is performed interactively in subsecond time by calling graph cut with each mouse movement. A renderable mesh is then computed automatically for the selected object and each of its subobjects by (1) generating a coarse object mesh; (2) performing recursive graph cut segmentation and hierarchical ordering of subobjects; (3) applying error-driven mesh refinement to each (sub)object. The fully layered object hierarchy compares favorably with current approaches and is computed in a few 10s of seconds, facilitating object-level editing without leaving holes.

Keywords

Image-based rendering and modeling Interaction techniques Computer vision for graphics Non-photorealistic rendering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ablameyko, S., Bereishik, V., Frantskevich, O., Homenko, M., Paramonova, N., Patsko, O.: Automatic/interactive interpretation of color map images. In: Proc. 16th Intl. Conf. on Pattern Recognition, pp. 1269–1272 (2002)Google Scholar
  2. 2.
    Adobe Systems Incorporated: Creative suite 2, streamline, macromedia flash, http://www.adobe.com/products (2005)Google Scholar
  3. 3.
    AutoTrace: Autotrace at http://autotrace.sourceforge.net/ (2004)Google Scholar
  4. 4.
    Barrett, W., Cheney, A.: Object-based image editing. In: Proceedings of ACM SIGGRAPH 2002, pp. 777–784 (2002)Google Scholar
  5. 5.
    Bertalmio, M., Sapiro, G., Vese, L., Ballester, C.: Image inpainting. In: Proceedings of ACM SIGGRAPH 2002, pp. 882–889 (2002)Google Scholar
  6. 6.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: Proceedings of IEEE International Conference on Computer Vision, pp. 105–112 (2001)Google Scholar
  7. 7.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. In: IEEE Transactions on PAMI, vol. 26, pp. 1124–1137 (2004)Google Scholar
  8. 8.
    Corel Corporation: CorelTRACE at http://www.corel.com (2005)Google Scholar
  9. 9.
    Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: Proceedings of IEEE CVPR 2003, pp. 721–728 (2003)Google Scholar
  10. 10.
    Kondo, T. (Highside): http://homepage3.nifty.com/highside/ (2004)Google Scholar
  11. 11.
    Li, Y., Sun, J., Tang, C.K., Shum, H.Y.: Lazy snapping. In: Proceedings of ACM SIGGRAPH 2004, pp. 303–308 (2004)Google Scholar
  12. 12.
    Mortensen, E.N., Barrett, W.A.: Toboggan-based intelligent scissors with a four parameter edge model. In: Proceedings of IEEE Conference on Computer vision and Pattern Recognition, pp. 452–458 (1999)Google Scholar
  13. 13.
    Reese, L., Barrett, W.: Image editing with intelligent paint. In: Proceedings of Eurographics 2002, vol. 21, pp. 714–724 (2002)Google Scholar
  14. 14.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut - interactive foreground extraction using iterated graph cuts. In: Proceedings of ACM SIGGRAPH 2004, pp. 309–314 (2004)Google Scholar
  15. 15.
    Siame Editions: Vector eye at http://www.siame.com/ (2005)Google Scholar
  16. 16.
    Sun, J., Yuan, L., Jia, J., Shum, H.Y.: Image completion with structure propatation. In: Proceedings of ACM SIGGRAPH 2005, pp. 861–868 (2005)Google Scholar
  17. 17.
    Yu X. Morse, B., Sederberg, T.: Image reconstruction using data-dependent triangulation. In: IEEE Computer Graphics and Applications, vol. 21, pp. 62–68 (2001)Google Scholar
  18. 18.
    Zou, J., Yan, H.: Line image vectorization based on shape partitioning and merging. In: Proc. Intl. Conf. on Pattern Recognition (2000)Google Scholar

Copyright information

© Springer-Verlag 2006

Authors and Affiliations

  1. 1.Brigham Young UniversityProvoUSA

Personalised recommendations