1 School of Computer Science and Technology, Shandong University, Jinan 250101, China;
2 Shandong Co-Innovation Center of Future Intelligent Computing, Yantai 264025, China;
3 School of Software, Shandong University, Jinan 250101, China;
4 Digital Media Research Institute, Shandong University of Finance and Economics, Jinan 250061, China
Abstract Image smoothing is a crucial image processing topic in image processing and has wide applied backgrounds. For images with rich texture, most of the existing image smoothing methods are difficult to obtain significant texture removal performance in many situations because textures containing obvious edges and large gradient changes are easy to be preserved as the main edges. In this paper, we propose a novel framework for image smoothing combined with the constraint of sparse high frequency gradient for texture image. First, we decompose the image into two components:a smooth component (constant component) and a non-smooth (high frequency) component. Second, we remove the non-smooth component containing high frequency gradient and smooth the other component combining with the constraint of sparse high frequency gradient. Experimental results demonstrate the proposed method is more competitive on efficiently texture removing than the state-of-the-art. What is more, our approach has a variety of applications including edge detection, detail magnification, image abstraction and image composition.
This work was supported by the National Natural Science Foundation of China under Grant Nos. 61373078, 61572292, 61602277, and 61332015, the Key Project of National Natural Science Foundation of China Joint Fund with Zhejiang Integration of Informatization and Industrialization under Grant No. U1609218, and the Natural Science Foundation of Shandong Province of China under Grant No. ZR2016FQ12.
Corresponding Authors: Xue-Mei Li
About author: Guang-Hao Ma is currently a M.S. student in the School of Computer Science and Technology, Shandong University, Jinan. He received his B.S. degree in computer science from Shandong University, Weihai, in 2015. His research interests include image smoothing and computer vision.
Cite this article:
Guang-Hao Ma, Ming-Li Zhang, Xue-Mei Li, Cai-Ming Zhang.Image Smoothing Based on Image Decomposition and Sparse High Frequency Gradient[J] Journal of Computer Science and Technology, 2018,V33(3): 502-510
 Rudin L I, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms. Physica D:Nonlinear Phenomena, 1992, 60(1/2/3/4):259-268. Tomasi C, Manduchi R. Bilateral filtering for gray and color images. In Proc. the 6th IEEE Int. Conf. Computer Vision, January 1998, pp.839-846. Farbman Z, Fattal R, Lischinski D, Szeliski R. Edgepreserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graphics, 2008, 27(3):Article No. 67. Subr K, Soler C, Durand F. Edge-preserving multiscale image decomposition based on local extrema. ACM Trans. Graphics, 2009, 28(5):Article No. 147. Cho S, Lee S. Fast motion deblurring. ACM Trans. Graphics, 2009, 28(5):Article No. 145. Xu L, Lu C W, Xu Y, Jia J Y. Image smoothing via L gradient minimization. ACM Trans. Graphics, 2011, 30(6):Article No. 174. Xu L, Yan Q, Xia Y, Jia J Y. Structure extraction from texture via relative total variation. ACM Trans. Graphics, 2012, 31(6):Article No. 139. Li X Y, Gu Y, Hu S M, Martin R R. Mixed-domain edgeaware image manipulation. IEEE Trans. Image Processing, 2013, 22(5):1915-1925. He K M, Sun J, Tang X O. Guided image filtering. IEEE Trans. Pattern Analysis and Machine Intelligence, 2013, 35(6):1397-1409. Karacan L, Erdem E, Erdem A. Structure-preserving image smoothing via region covariances. ACM Trans. Graphics, 2013, 32(6):Article No. 176. Min D B, Choi S, Lu J B, Ham B, Sohn K, Do M N. Fast global image smoothing based on weighted least squares. IEEE Trans. Image Processing, 2014, 23(12):5638-5653. Zhang Q, Shen X Y, Xu L, Jia J Y. Rolling guidance filter. In Proc. the 13th European Conf. Computer Vision, September 2014, pp.815-830. Bao L C, Song Y B, Yang Q X, Yuan H, Wang G. Tree filtering:Efficient structure-preserving smoothing with a minimum spanning tree. IEEE Trans. Image Processing, 2014, 23(2):555-569. Bi S, Han X G, Yu Y Z. An L1 image transform for edgepreserving smoothing and scene-level intrinsic decomposition. ACM Trans. Graphics, 2015, 34(4):Article No. 78. Paris S, Hasinoff S W, Kautz J. Local Laplacian filters:Edge-aware image processing with a Laplacian pyramid. Communications of the ACM, 2015, 58(3):81-91. Zang Y, Huang H, Zhang L. Guided adaptive image smoothing via directional anisotropic structure measurement. IEEE Trans. Visualization and Computer Graphics, 2015, 21(9):1015-1027. Liu Q, Zhang C M, Guo Q, Zhou Y F. A nonlocal gradient concentration method for image smoothing. Computational Visual Media, 2015, 1(3):197-209. Zheng S F, Song C W, Zhang H Z, Yan Z F, Zuo W M. Learning-based weighted total variation for structure preserving texture removal. In Proc. Chinese Conf. Pattern Recognition, November 2016, pp.147-160. Gu S H, Zuo W M, Xie Q, Meng D Y, Feng X C, Zhang L. Convolutional sparse coding for image super-resolution. In Proc. IEEE Int. Conf. Computer Vision, December 2015, pp.1823-1831. Zhang M L, Desrosiers C. Image completion with global structure and weighted nuclear norm regularization. In Proc. IEEE Int. Joint Conf. Neural Networks, May 2017, pp.4187-4193. Lu S P, Dauphin G, Lafruit G, Munteanu A. Color retargeting:Interactive time-varying color image composition from time-lapse sequences. Computational Visual Media, 2015, 1(4):321-330. Wu L Q, Liu Y P, Brekhna, Liu N, Zhang C M. Highresolution images based on directional fusion of gradient. Computational Visual Media, 2016, 2(1):31-43. Li Q H, Fang Y M, Xu J T. A novel spatial pooling strategy for image quality assessment. Journal of Computer Science and Technology, 2016, 31(2):225-234. Xie H, Tong R. Patch-based variational image approximation. Science China Information Sciences, 2017, 60(3):032104. Du H W, Zhang Y F, Bao F X, Wang P, Zhang C M. A texture feature preserving image interpolation algorithm via gradient constraint. Communications in Information and Systems, 2016, 16(4):203-227. Meyer Y. Oscillating Patterns in Image Processing and Nonlinear Evolution Equations:The Fifteenth Dean Jacqueline B. Lewis Memorial Lectures. American Mathematical Society, 2001. Yin W T, Goldfarb D, Osher S. Image cartoon-texture decomposition and feature selection using the total variation regularized L1 functional. In Proc. Variational Geometric and Level Set Methods in Computer Vision, October 2005, pp.73-84. Aujol J F, Gilboa G, Chan T, Osher S. Structure-texture image decomposition-modeling, algorithms, and parameter selection. International Journal of Computer Vision, 2006, 67(1):111-136. Wang Y L, Yang J T, Yin W T, Zhang Y. A new alternating minimization algorithm for total variation image reconstruction. SIAM Journal on Imaging Sciences, 2008, 1(3):248-272. Zhang S H, Li X Y, Hu S M, Martin R R. Online video stream abstraction and stylization. IEEE Trans. Multimedia, 2011, 13(6):1286-1294. Pérez P, Gangnet M, Blake A. Poisson image editing. ACM Trans. Graphics, 2003, 22(3):313-318.
Copyright 2010 by Journal of Computer Science and Technology