Science Journal of Circuits, Systems and Signal Processing

| Peer-Reviewed |

Stream Flow Painting from Real Images Using Anisotropic Band-Pass Filter

Received: 20 September 2014    Accepted: 28 January 2015    Published: 27 February 2015
Views:       Downloads:

Share This Article

Abstract

A new non-photorealistic rendering algorithm is proposed for creating artistic painting with soft stream flow from natural color images. The algorithm consists mainly of two stages, that is, a revised bilateral filter called trilateral filter is firstly applied to original color image for creating drawings using gradient information and then a DoG-like band-pass filter is adapted for generating soft stream flow along the eigenvectors and therefore the image is smoothed along curved stream lines. The proposed trilateral filter is an extension of bilateral filter by incorporating gradient space. On the other hand, DoG-like band-pass filter is designed by applying eigenvectors and eigenvalues of a structure tensor matrix calculated at each pixel. Our approach effectively preserves image main structures while smoothing image regions in an anisotropic way. Even in regions with lower contrast, stream flow-like potential structures are also well produced due to a gradient relaxation. The experiments demonstrate that the proposed algorithm works well and produces good and pleasant visual results.

DOI 10.11648/j.cssp.s.2014030601.15
Published in Science Journal of Circuits, Systems and Signal Processing (Volume 3, Issue 6-1, December 2014)

This article belongs to the Special Issue Computational Intelligence in Digital Image Processing

Page(s) 30-38
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Anisotropic Filter, DoG-Like Band-Pass Filter, Trilateral Filter, Stream Flow Painting

References
[1] B. Gooch and A. Gooch, Non-Photorealistic Rendering, A K Peters, Ltd., 2001.
[2] T. Strothotte and S. Stefan, Non-Photorealistic Computer Graphics: Modelling, Rendering and Animation, Morgan Kaufmann, 2002.
[3] O. Deussen, S. Hiller C. Van Overveld and T. Strothotte, Floating Points: A Method for Computing Stipple Drawings, Computer Graphics Forum, Vol.19, No.3, 40-51, 2000.
[4] A. Secord, Weighted Voronoi Stippling, In Proc NPAR, ACM Press, New York, pp.37-43, 2002.
[5] Kim, D., Son, M., Lee, Y., Kang, H., and Lee, S. Feature-guided Image Stippling. In Proceedings of Comput. Graph. Forum. 2008, pp. 1209-1216.
[6] M. P. Salisbury, S. E. Anderson, R. Barzel, and D. H. Salesin, Interactive Pen-and-Ink Illustration. In ACM SIGGRAPH 94 Conference Proceedings, pp. 101-108, July 1994.
[7] D. Decarlo, A. Finkelstein, S. Rusinkiewicz and A. Santella, Suggestive Contour for Conveying Shape, In Proceedings of ACM SIGGRAPH, pp. 848-855, 2003.
[8] T. Judd, F.Durand and E. Andelson, Apparent Ridges for Line Drawing, In Proceeding of ACM SIGGRAPH, 2007.
[9] H. Kang, S. Lee, C. Chui. "Coherent Line Drawing". Proc. ACM Symposium on Non-photorealistic Animation and Rendering, pp. 43-50, San Diego, CA, 2007.
[10] M. Son, H. Kang, Y. Lee, S. Lee. "Abstract Line Drawings from 2D Images". Proc. Pacific Graphics, IEEE Press, pp. 333-342, Maui, Hawaii, 2007.
[11] A. Hertzmann, Tutorial: A Survey of Stroke-Based Rendering, IEEE Computer Graphics and Application, Vol.23, No.4, pp. 70-81, 2003.
[12] A. Hertzmann, Painterly Rendering with Curved Brush Strokes of Multiple Sizes, In Proceeding of the 25th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH 1998), pp. 453-460.
[13] K. Zeng, M. Zhao, C. Xiong, and S.C. Zhu, "From image parsing to painterly rendering", presented at ACM Trans. Graph., 2009.
[14] G. Papari, N. Petkov, and P. Campisi, Artistic Edge and Corner Enhancing Smoothing, IEEE Trans. Image Processing, Vol. 16, No. 10, pp.2449-2462, 2007.
[15] H. Kang, S. Lee, and C. K. Chui, Flow-Based Image Abstraction, IEEE Trans. Visualization and Computer Graphics, Vol. 15, No. 1, pp. 62-76, 2009.
[16] J. E. Kyprianidis and H. Kang, Image and Video Abstraction by Coherence-Enhancing Filtering, Computer Graphics Forum, Vol. 30, No. 2, (Proceedings Eurographics 2011)
[17] M. Nixon, and A. Aguado, Feature Extraction and Image Processing (2nd. ed.), Elsevier Ltd. 2008.
[18] C. Tomasi, and R. Manduchi, Bilateral Filtering for Gray and Color Images, In Proc. of IEEE International Conference on Computer Vision, pp.839-846, 1998.
[19] K. He, J. Sun and X. Tang, Guided Image Filter, IEEE Trans. On Pattern Analysis and Machine Intelligence, Vol. 35, No. 6, pp.1397-1409, 2013.
[20] M. Kuwahara, K. Hachimura, S. Ehiu, and M. Kinoshita, Processing of ri-angiocardiographic images, In Digital Processing of Biomedical Images, New York: Plenum, pp. 187-203, 1976.
[21] J. E. Kyprianidis, H. Kang, and J. Dollner, Image and Video Abstraction by Anisotropic Kuwahara Filtering, Computer Graphics Forum, Vol. 28, No.7, pp.1955-1963, 2009.
[22] M. Kass and D. Pesare, Coherent Noise for Non-Photorealistic Rendering, ACM Trans. On Graphics, Vol. 30, No. 4, Article 30, July 2011.
[23] M. Zhao and S. Zhu, Abstract Painting with Interactive Control of Perceptual Entropy, ACM Trans. On Applied Perception, Vol. 10, No. 1, February 2013.
[24] N. Xie, H. Hachiya and M. Sugiyama, Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting, Proc. Of the 29th International Conference on Machine Learning, pp.153-160, 2012.
[25] N. Xie, H. Hachiya and M. Sugiyama, Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting, IEICE Trans. INF. & SYST. Vol. E96-D, No. 5, May 2013.
[26] S. Osher and L. I. Rudin, Feature-Oriented Image Enhancement Using Shock Filter, SIAM Journal on Numerical Analysis, Vol. 27, 919-940, 1990.
[27] J. Werckert, Coherence-Enhancing Diffusion of Color Image, Image and Vision Computing, Vol.17, No. 3, pp. 201-212, 1999.
[28] J. Werckert, Coherence-Enhancing Shock Filters, Pattern Recognition, Lect. Notes in Comput. Sc. 2781, pp. 1-8, 2003.
[29] J. E. Kyprianidis, and J. Dollner, Image Abstraction by Structure Adaptive Filtering, In Proc. EG UK Theory and Practice of Computer Graphics, pp. 51-58, 2008.
[30] H. Kang and S. Lee, Shape-simplifying Image Abstraction, Computer Graphics Forum, Vol. 27, No. 7, pp. 1773-1780, 2008.
[31] M. Bertalmio, G. Sapiro, V. Caselles and C. Ballester, Image Inpainting, Proceedings of SIGGRAPH 2000, New Orleans, USA, July 2000.
[32] K. Inoue and K. Urahama, Anisotropic Bilateral Filters for Edge-Preserving Stripe Enhancement, ITE, Vol. 58, No. 1, pp.115-120, 2004.
[33] P. Choudhury and Jack Tumblin, The Trilateral for High Contrast Images and Meshes, Erographics Symposium on Rendering 2003, pp.186-196.
[34] J. B. Shen, S. F. Fang, H. L. Zhao and X. G. Jin, Fast Approximation of Trilateral Filter for Tone Mapping Using a Signal Processing Approach, Signal Processing, Vol. 89, No. 5, May 2009, pp. 901-907.
[35] W. C. K. Wong, A. C. S. Chung and S. C. H. Yu, Trilateral Filtering for Biomedical Images, in Proc. IEEE Int. Symp. Biomedical Imaging, 2004, pp.820-823.
[36] D. Mould, Authorial Subjective Evaluation of Non-Photorealistic Images, NPAR '14 Proceedings of the Workshop on Non-Photorealistic Animation and Rendering, Pages 49-56.
Author Information
  • Department of Information System and Management, Hiroshima Institute of Technology, Hiroshima, Japan

  • School of Software Engineering, Tongji University, Shanghai, China

  • Department of Physics, Qinghai Normal University, Xining, China

  • School of Computer Science, Qinghai Normal University, Xining, China

Cite This Article
  • APA Style

    Xiaohua Zhang, Ning Xie, Yuelan Xin, Heming Huang. (2015). Stream Flow Painting from Real Images Using Anisotropic Band-Pass Filter. Science Journal of Circuits, Systems and Signal Processing, 3(6-1), 30-38. https://doi.org/10.11648/j.cssp.s.2014030601.15

    Copy | Download

    ACS Style

    Xiaohua Zhang; Ning Xie; Yuelan Xin; Heming Huang. Stream Flow Painting from Real Images Using Anisotropic Band-Pass Filter. Sci. J. Circuits Syst. Signal Process. 2015, 3(6-1), 30-38. doi: 10.11648/j.cssp.s.2014030601.15

    Copy | Download

    AMA Style

    Xiaohua Zhang, Ning Xie, Yuelan Xin, Heming Huang. Stream Flow Painting from Real Images Using Anisotropic Band-Pass Filter. Sci J Circuits Syst Signal Process. 2015;3(6-1):30-38. doi: 10.11648/j.cssp.s.2014030601.15

    Copy | Download

  • @article{10.11648/j.cssp.s.2014030601.15,
      author = {Xiaohua Zhang and Ning Xie and Yuelan Xin and Heming Huang},
      title = {Stream Flow Painting from Real Images Using Anisotropic Band-Pass Filter},
      journal = {Science Journal of Circuits, Systems and Signal Processing},
      volume = {3},
      number = {6-1},
      pages = {30-38},
      doi = {10.11648/j.cssp.s.2014030601.15},
      url = {https://doi.org/10.11648/j.cssp.s.2014030601.15},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.cssp.s.2014030601.15},
      abstract = {A new non-photorealistic rendering algorithm is proposed for creating artistic painting with soft stream flow from natural color images. The algorithm consists mainly of two stages, that is, a revised bilateral filter called trilateral filter is firstly applied to original color image for creating drawings using gradient information and then a DoG-like band-pass filter is adapted for generating soft stream flow along the eigenvectors and therefore the image is smoothed along curved stream lines. The proposed trilateral filter is an extension of bilateral filter by incorporating gradient space. On the other hand, DoG-like band-pass filter is designed by applying eigenvectors and eigenvalues of a structure tensor matrix calculated at each pixel. Our approach effectively preserves image main structures while smoothing image regions in an anisotropic way. Even in regions with lower contrast, stream flow-like potential structures are also well produced due to a gradient relaxation. The experiments demonstrate that the proposed algorithm works well and produces good and pleasant visual results.},
     year = {2015}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Stream Flow Painting from Real Images Using Anisotropic Band-Pass Filter
    AU  - Xiaohua Zhang
    AU  - Ning Xie
    AU  - Yuelan Xin
    AU  - Heming Huang
    Y1  - 2015/02/27
    PY  - 2015
    N1  - https://doi.org/10.11648/j.cssp.s.2014030601.15
    DO  - 10.11648/j.cssp.s.2014030601.15
    T2  - Science Journal of Circuits, Systems and Signal Processing
    JF  - Science Journal of Circuits, Systems and Signal Processing
    JO  - Science Journal of Circuits, Systems and Signal Processing
    SP  - 30
    EP  - 38
    PB  - Science Publishing Group
    SN  - 2326-9073
    UR  - https://doi.org/10.11648/j.cssp.s.2014030601.15
    AB  - A new non-photorealistic rendering algorithm is proposed for creating artistic painting with soft stream flow from natural color images. The algorithm consists mainly of two stages, that is, a revised bilateral filter called trilateral filter is firstly applied to original color image for creating drawings using gradient information and then a DoG-like band-pass filter is adapted for generating soft stream flow along the eigenvectors and therefore the image is smoothed along curved stream lines. The proposed trilateral filter is an extension of bilateral filter by incorporating gradient space. On the other hand, DoG-like band-pass filter is designed by applying eigenvectors and eigenvalues of a structure tensor matrix calculated at each pixel. Our approach effectively preserves image main structures while smoothing image regions in an anisotropic way. Even in regions with lower contrast, stream flow-like potential structures are also well produced due to a gradient relaxation. The experiments demonstrate that the proposed algorithm works well and produces good and pleasant visual results.
    VL  - 3
    IS  - 6-1
    ER  - 

    Copy | Download

  • Sections