Real-time Image Vectorization on GPU

Xiaoliang Xiong, Jie Feng, Bingfeng Zhou

2016

Abstract

In this paper, we present a novel algorithm to convert a raster image into its vector form. Different from the state-of-art methods, we explore the potential parallelism that exists in the problem and propose an algorithm suitable to be accelerated by the graphics hardware. In our algorithm, the vectorization task is decomposed into four steps: detecting the boundary pixels, pre-computing the connectivity relationship of detected pixels, organizing detected pixels into boundary loops and vectorizing each loop into line segments. The boundary detection and connectivity pre-computing are parallelized owing to the independence between scanlines. After a sequential boundary pixels organizing, all loops are vectorized concurrently. With a GPU implementation, the vectorization can be accomplished in real-time. Then, the image can be represented by the vectorized contour. This real-time vectorization algorithm can be used on images with multiple silhouettes and multi-view videos. We demonstrate the efficiency of our algorithm with several applications including cartoon and document vectorization.

References

  1. Chang, F., Lu, Y.-C., and Pavlidis, T. (1999). Feature analysis using line sweep thinning algorithm. IEEE Dori, D. and Liu, W. (1999). Sparse pixel vectorization: An algorithm and its performance evaluation. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 21(3):202-215.
  2. Jimenez, J. and Navalon, J. L. (1982). Some experiments in image vectorization. IBM Journal of research and Development, 26(6):724-734.
  3. Kass, M., Witkin, A., and Terzopoulos, D. (1988). Snakes: Active Contour Models. International Journal of Computer Vision, 1(4):321-331.
  4. Ladikos, A., Benhimane, S., and Navab, N. (2008). Efficient visual hull computation for real-time 3d reconstruction using cuda. pages 1-8.
  5. Laurentini, A. (1994). The visual hull concept for silhouette-based image understanding. Pattern Analysis and Machine Intelligence, 16(2):150-162.
  6. Li, M., Magnor, M., and Seidel, H.-P. (2004). A hybrid hardware-accelerated algorithm for high quality rendering of visual hulls. In Proceedings of Graphics Interface 2004, pages 41-48. Canadian Human-Computer Communications Society.
  7. Matusik, W., Buehler, C., Raskar, R., Gortler, S. J., and McMillan, L. (2000). Image-based visual hulls. In SIGGRAPH 2000, pages 369-374. ACM.
  8. Nehab, D. and Hoppe, H. (2008). Random-access rendering of general vector graphics. In ACM Transactions on Graphics (TOG), volume 27, page 135. ACM.
  9. Orzan, A., Bousseau, A., Barla, P., Winnemöller, H., Thollot, J., and Salesin, D. (2013). Diffusion curves: a vector representation for smooth-shaded images. ACM Transactions on Graphics, 56(7):101-108.
  10. Smith, R. W. (1987). Computer processing of line images: A survey. Pattern recognition, 20(1):7-15.
  11. Sun, J., Liang, L., Wen, F., and Shum, H.-Y. (2007). Image vectorization using optimized gradient meshes. In ACM Transactions on Graphics (TOG), volume 26, page 11. ACM.
  12. Waizenegger, W., Feldmann, I., Eisert, P., and Kauff, P. (2009). Parallel high resolution real-time visual hull on gpu. In Image Processing (ICIP), 2009 16th IEEE International Conference on, pages 4301-4304.
  13. Xia, T., Liao, B., and Yu, Y. (2009). Patch-based image vectorization with automatic curvilinear feature alignment. In ACM Transactions on Graphics (TOG), volume 28, page 115. ACM.
  14. Yous, S., Laga, H., Kidode, M., and Chihara, K. (2007). Gpu-based shape from silhouettes. In Proceedings of the 5th international conference on Computer graphics and interactive techniques in Australia and Southeast Asia, pages 71-77. ACM.
  15. Zhang, S.-H., Chen, T., Zhang, Y.-F., Hu, S.-M., and Martin, R. R. (2009). Vectorizing cartoon animations. IEEE Transactions on Visualization and Computer Graphics, 15(4):618-629.
  16. Zhao, J., Feng, J., and Zhou, B. (2013). Image vectorization using blue-noise sampling. In IS&T/SPIE Electronic Imaging, pages 86640H-86640H. International Society for Optics and Photonics.
  17. Zou, J. J. and Yan, H. (2001). Cartoon image vectorization based on shape subdivision. In Computer Graphics International 2001. Proceedings, pages 225-231. IEEE.
Download


Paper Citation


in Harvard Style

Xiong X., Feng J. and Zhou B. (2016). Real-time Image Vectorization on GPU . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 143-150. DOI: 10.5220/0005668901410148


in Bibtex Style

@conference{grapp16,
author={Xiaoliang Xiong and Jie Feng and Bingfeng Zhou},
title={Real-time Image Vectorization on GPU},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2016)},
year={2016},
pages={143-150},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005668901410148},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2016)
TI - Real-time Image Vectorization on GPU
SN - 978-989-758-175-5
AU - Xiong X.
AU - Feng J.
AU - Zhou B.
PY - 2016
SP - 143
EP - 150
DO - 10.5220/0005668901410148