Abstract
In this paper, we present a novel algorithm to convert the contour in 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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chang, F., Lu, Y.-C., Pavlidis, T.: Feature analysis using line sweep thinning algorithm. IEEE Trans. Pattern Anal. Mach. Intell. 21(2), 145–158 (1999)
Dori, D., Liu, W.: Sparse pixel vectorization: an algorithm and its performance evaluation. IEEE Trans. Pattern Anal. Mach. Intell. 21(3), 202–215 (1999)
Jimenez, J., Navalon, J.L.: Some experiments in image vectorization. IBM J. Res. Dev. 26(6), 724–734 (1982)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1(4), 321–331 (1988)
Ladikos, A., Benhimane, S., Navab, N.: Efficient visual hull computation for real-time 3d reconstruction using CUDA, pp. 1–8 (2008)
Laurentini, A.: The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 150–162 (1994)
Li, M., Magnor, M., Seidel, H.-P.: A hybrid hardware-accelerated algorithm for high quality rendering of visual hulls. In: Proceedings of Graphics Interface 2004, pp. 41–48. Canadian Human-Computer Communications Society (2004)
Matusik, W., Buehler, C., Raskar, R., Gortler, S.J., McMillan, L.: Image-based visual hulls. In: SIGGRAPH 2000, pp. 369–374. ACM (2000)
Nehab, D., Hoppe, H.: Random-access rendering of general vector graphics. In: ACM Transactions on Graphics (TOG), vol. 27, p. 135. ACM(2008)
Orzan, A., Bousseau, A., Barla, P., Winnemöller, H., Thollot, J., Salesin, D.: Diffusion curves: a vector representation for smooth-shaded images. ACM Trans. Graph. 56(7), 101–108 (2013)
Smith, R.W.: Computer processing of line images: a survey. Pattern Recogn. 20(1), 7–15 (1987)
Sun, J., Liang, L., Wen, F., Shum, H.-Y.: Image vectorization using optimized gradient meshes. In: ACM Transactions on Graphics (TOG), vol. 26, p. 11. ACM (2007)
Waizenegger, W., Feldmann, I., Eisert, P., Kauff, P.: Parallel high resolution real-time visual hull on GPU. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pp. 4301–4304 (2009)
Xia, T., Liao, B., Yu, Y.: Patch-based image vectorization with automatic curvilinear feature alignment. In: ACM Transactions on Graphics (TOG), vol. 28, p. 115. ACM (2009)
Yous, S., Laga, H., Kidode, M., Chihara, K.: GPU-based shape from silhouettes. In: Proceedings of the 5th International Conference on Computer Graphics and Interactive Techniques in Australia and Southeast Asia, pp. 71–77. ACM (2007)
Zhang, S.-H., Chen, T., Zhang, Y.-F., Hu, S.-M., Martin, R.R.: Vectorizing cartoon animations. IEEE Trans. Vis. Comput. Graph. 15(4), 618–629 (2009)
Zhao, J., Feng, J., and Zhou, B.: Image vectorization using blue-noise sampling. In: IS&T/SPIE Electronic Imaging, p. 86640H. International Society for Optics and Photonics (2013)
Zou, J.J., Yan, H.: Cartoon image vectorization based on shape subdivision. In: Proceedings of the Computer Graphics International 2001, pp. 225–231. IEEE (2001)
Acknowledgements
This work is partially supported by NSFC grants #61170206, #61370112, and Specialized Research Fund for the Doctoral Program of Higher Education #20110001110077.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Xiong, X., Feng, J., Zhou, B. (2017). Real-Time Contour Image Vectorization on GPU. In: Braz, J., et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2016. Communications in Computer and Information Science, vol 693. Springer, Cham. https://doi.org/10.1007/978-3-319-64870-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-64870-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64869-9
Online ISBN: 978-3-319-64870-5
eBook Packages: Computer ScienceComputer Science (R0)