Journal Home > Volume 1 , Issue 3
Computational Visual Media 2015, 1(3): 197-209 https://doi.org/10.1007/s41095-015-0012-6
Research Article | Open Access | Issue | Published: 14 August 2015

A nonlocal gradient concentration method for image smoothing

Show Author's Information Qian Liu1,  Caiming Zhang1,2,  Qiang Guo1,2,  Yuanfeng Zhou1( )
School of Computer Science and Technology, Shandong University, Jinan 250101, China.
Shandong University of Finance and Economics, Shandong Provincial Key Laboratory of Digital Media Technology, Jinan 250014, China.
Keywords:
edge detection, image smoothing, nonlocal similarity, L0 norm
Cite this article:
Liu Q, Zhang C, Guo Q, et al. A nonlocal gradient concentration method for image smoothing. Computational Visual Media, 2015, 1(3): 197-209. https://doi.org/10.1007/s41095-015-0012-6
Download citation
EndNote(RIS)
BibTeX

644

Views

44

Downloads

Citations

13

Crossref

N/A

WoS

15

Scopus

0

CSCD

Abstract Full text About this article

It is challenging to consistently smooth natural images, yet smoothing results determine the quality of a broad range of applications in computer vision. To achieve consistent smoothing, we propose a novel optimization model making use of the redundancy of natural images, by defining a nonlocal concentration regularization term on the gradient. This nonlocal constraint is carefully combined with a gradient-sparsity constraint, allowing details throughout the whole image to be removed automatically in a data-driven manner. As variations in gradient between similar patches can be suppressed effectively, the new model has excellent edge preserving, detail removal, and visual consistency properties. Comparisons with state-of-the-art smoothing methods demonstrate the effectiveness of the new method. Several applications, including edge manipulation, image abstraction, detail magnification, and image resizing, show the applicability of the new method.


menu
Abstract
Full text
Outline
About this article

A nonlocal gradient concentration method for image smoothing

Show Author's information Qian Liu1, Caiming Zhang1,2, Qiang Guo1,2, Yuanfeng Zhou1( )
School of Computer Science and Technology, Shandong University, Jinan 250101, China.
Shandong University of Finance and Economics, Shandong Provincial Key Laboratory of Digital Media Technology, Jinan 250014, China.

Abstract

It is challenging to consistently smooth natural images, yet smoothing results determine the quality of a broad range of applications in computer vision. To achieve consistent smoothing, we propose a novel optimization model making use of the redundancy of natural images, by defining a nonlocal concentration regularization term on the gradient. This nonlocal constraint is carefully combined with a gradient-sparsity constraint, allowing details throughout the whole image to be removed automatically in a data-driven manner. As variations in gradient between similar patches can be suppressed effectively, the new model has excellent edge preserving, detail removal, and visual consistency properties. Comparisons with state-of-the-art smoothing methods demonstrate the effectiveness of the new method. Several applications, including edge manipulation, image abstraction, detail magnification, and image resizing, show the applicability of the new method.

Keywords: edge detection, image smoothing, nonlocal similarity, L0 norm

References(22)

[1]
Arnheim R. Art and Visual Perception: A Psychology of the Creative Eye. University of California Press, 1954.
[2]
Tomasi C.; Manduchi R. Bilateral filtering for gray and color images. In: Proceedings of the Sixth International Conference on Computer Vision, 839, 1998.
[3]
He K.; Sun J.; Tang X. Guided image filtering. Lecture Notes in Computer Science Vol. 6311, 1-14, 2010.
DOI Google Scholar
[4]
Paris S.; Hasinoff S. W.; Kautz J. Local Laplacian filters: Edge-aware image processing with a Laplacian pyramid. ACM Transactions on Graphics Vol. 30, No. 4, Article No. 68, 2011.
DOI Google Scholar
[5]
Rudin L. I.; Osher S.; Fatemi E. Nonlinear total variation based noise removal algorithms. Physica D: Nonlinear Phenomena Vol. 60, Nos. 1–4, 259-268, 1992.
DOI Google Scholar
[6]
Farbman Z.; Fattal R.; Lischinski D.; Szeliski R. Edgepreserving decompositions for multi-scale tone and detail manipulation. ACM Transactions on Graphics Vol. 27, No. 3, Article No. 67, 2008.
DOI Google Scholar
[7]
Xu L.; Lu C.; Xu Y.; Jia J. Image smoothing via L gradient minimization. ACM Transactions on Graphics Vol. 30, No. 6, Article No. 174, 2011.
DOI Google Scholar
[8]
Subr K.; Soler C.; Durand F. Edge-preserving multiscale image decomposition based on local extrema. ACM Transactions on Graphics Vol. 28, No. 5, Article No. 147, 2009.
DOI Google Scholar
[9]
Steidl G.; Teuber T. Anisotropic smoothing using double orientations. Lecture Notes in Computer Science Vol. 5567, 477-489, 2009.
DOI Google Scholar
[10]
Kyprianidis J. E.; Kang H. Image and video abstraction by coherence-enhancing filtering. Computer Graphics Forum Vol. 30, No. 2, 593-602, 2011.
DOI Google Scholar
[11]
Xu L.; Yan Q.; Xia Y.; Jia J. Structure extraction from texture via relative total variation. ACM Transactions on Graphics Vol. 31, No. 6, Article No. 139, 2012.
DOI Google Scholar
[12]
Karacan L.; Erdem E.; Erdem A. Structure-preserving image smoothing via region covariances. ACM Transactions on Graphics Vol. 32, No. 6, Article No. 176, 2013.
DOI Google Scholar
[13]
Su Z.; Luo X.; Artusi A. A novel image decomposition approach and its applications. The Visual Computer Vol. 29, No. 10, 1011-1023, 2013.
DOI Google Scholar
[14]
Li X.-Y.; Gu Y.; Martin R. R.; Hu S.-M. Mixed-domain edge-aware image manipulation. IEEE Transactions on Image Processing Vol. 22, No. 5, 1915-1925, 2013.
DOI Google Scholar
[15]
Bao L.; Song Y.; Yang Q.; Yuan H.; Wang G. Tree filtering: Efficient structure-preserving smoothing with a minimum spanning tree. IEEE Transactions on Image Processing Vol. 23, No. 2, 555-569, 2014.
DOI Google Scholar
[16]
Zhang Q.; Shen X.; Xu L.; Jia J. Rolling guidance filter. Lecture Notes in Computer Science Vol. 8691, 815-830, 2014.
DOI Google Scholar
[17]
Zang Y.; Huang H.; Zhang L. Efficient structure-aware image smoothing by local extrema on space-filling curve. IEEE Transactions on Visualization and Computer Graphics Vol. 20, No. 9, 1253-1265, 2014.
DOI Google Scholar
[18]
Buades A.; Coll B.; Morel J.-M. A non-local algorithm for image denoising. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 60-65, 2005.
[19]
Wang Y.; Yang J.; Yin W.; Zhang Y. A new alternating minimization algorithm for total variation image reconstruction. SIAM Journal on Imaging Sciences Vol. 1, No. 3, 248-272, 2008.
DOI Google Scholar
[20]
Zhang S.-H.; Li X.-Y.; Hu S.-M.; Martin R. R. Online video stream abstraction and stylization. IEEE Transactions on Multimedia Vol. 13, No. 6, 1286-1294, 2011.
DOI Google Scholar
[21]
Wong F. J.; Takahashi S. Abstracting images into continuousline artistic styles. The Visual Computer Vol. 29, Nos. 6–8, 729-738, 2013.
DOI Google Scholar
[22]
Avidan S.; Shamir A. Seam carving for content-aware image resizing. ACM Transactions on Graphics Vol. 26, No. 3, Article No. 10, 2007.
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Revised: 19 December 2014
Accepted: 02 April 2015
Published: 14 August 2015
Issue date: September 2015

Copyright

© The Author(s) 2015

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Nos. 61332015, 61373078, 61272245, 61202148, and 61103150), and the NSFC-Guangdong Joint Fund (No. U1201258).

Rights and permissions

This article is published with open access at Springerlink.com

This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution, and reproduction in any medium, provided the original author(s) and the source are credited.

Other papers from this open access journal are available at no cost from http://www.springer.com/journal/41095. To submit a manuscript, please go to https://www.editorialmanager.com/cvmj.

Return