Abstract
In this paper, a new model for structure/texture decomposition using a local gradient constraint is presented. This constraint is used because gradients of the structure component \(u\) are close to the gradients of a given noise-free image \(f\) in locally piecewise smooth regions. We consider the TV-Hilbert model as a blur and deblur process for image decomposition. By incorporating the additional local constraint of the image gradient into the classical TV-Hilbert model, we derive a new image decomposition model. The proposed model can separate the texture component \(v\) from \(f\) effectively while preserving sharp edges and maintaining homogeneous regions in the structure component \(u\) without producing staircase artifacts. Numerical experiments are performed to demonstrate the efficiency of our model in comparison with well-known image decomposition approaches.
Similar content being viewed by others
References
Andreu-Vaillo, F., Caselles, V., Mazón, J.M.: Parabolic Quasilinear Equations Minimizing Linear Growth Functionals, Progress in Mathematics 223. Birkhäuser, Basel (2004)
Aujol, J.-F., Aubert, G., Blanc-Féraud, L., Chambolle, A.: Image decomposition into a bounded variation component and an oscillating component. J. Math. Imaging Vis. 22, 71–88 (2005)
Aujol, J.-F., Chambolle, A.: Dual norms and image decomposition models. Int. J. Comput. Vis. 63, 85–104 (2005)
Aujol, J.-F., Gilboa, G.: Implementation and parameter selection for BV-Hilbert space regularization. CAM Report 04–66, UCLA, Los Angeles, CA (2004)
Aujol, J.-F., Gilboa, G., Chan, T.F., Osher, S.: Structure–texture decomposition by a TV-Gabor model. Lect. Notes Comput. Sci. 3752, 85–96 (2005)
Aujol, J.-F., Gilboa, G., Chan, T.F., Osher, S.: Structure–texture image decompositon-modeling, algorithms, and parameter selection. Int. J. Comput. Vis. 67, 111–136 (2006)
Buades, A., Le, T.M., Morel, J.-M., Vese, L.A.: Fast cartoon + texture image filters. IEEE Trans. Image Process. 19, 1978–1986 (2010)
Chambolle, A., Lions, P.-L.: Image recovery via total variation minimization and related problems. Numer. Math. 76, 167–188 (1997)
Chambolle, A.: An algorithm for total variation minimization and applications. J. Math. Imaging Vis. 20, 89–97 (2004)
Chan, T.F., Esedoglu, S.: Aspects of total variation regularized L1 function approximation. SIAM J. Appl. Math. 65, 1817–1837 (2005)
Chan, T.F., Esedoglu, S., Park, F.E.: Image decomposition combining staircase reduction and texture extraction. J. Vis. Commun. Image R. 18, 464–486 (2007)
Choudhury, P., Tumblin, J.: The trilateral filter for high contrast images and meshes. In: Proceedings of the Eurographics Symposium on Rendering, pp. 186–196 (2003)
Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graphic. 27, 67:1–67:10 (2008)
Garnett, J.B., Le, T.M., Meyer, Y., Vese, L.A.: Image decompositions using bounded variation and generalized homogeneous Besov spaces. Appl. Comput. Harmon. Anal. 23, 25–56 (2007)
Goldstein, T., Osher, S.: The split Bregman method for L1 regularized problems. SIAM J. Imaging Sci. 2, 323–343 (2009)
Jones, P.W., Le, T.M.: Local scales and multiscale image decompositions. Appl. Comput. Harmon. Anal. 26, 371–394 (2009)
Le, T.M., Vese, L.A.: Image decomposition using total variation and div(BMO). Multiscale Model. Simul. 4, 390–423 (2005)
Lieu, L., Vese, L.A.: Image restoration and decomposition via bounded total variation and negative Hilbert-Sobolev spaces. CAM Report 05–33, UCLA, Los Angeles, CA (2005)
Meyer, Y.: Oscillating patterns in image processing and nonlinear evolution equations. In: The Fifteenth Dean Jacqueline B. Lewis Memorial Lectures. Amer. Math. Soc, Boston, MA (2001)
Osher, S., Solé, A., Vese, L.: Image decomposition and restoration using total variation minimization and the \(H^{-1}\) norm. Multiscale Model. Simul. 1, 349–370 (2003)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12, 629–639 (1990)
Qiegen, L., Jianhua, L., Yuemin, Z.: Adaptive image decomposition by improved bilateral filter. Int. J. Comput. Appl. 23, 16–22 (2011)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithm. Phys. D 60, 259–268 (1992)
Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. 27, 73:1–73:10 (2008)
Su, S.L., Durand, F., Agrawala, M.: De-emphasis of distracting image regions using texture power maps. In Proceedings of 4th ICCV Workshop on Texture Analysis and Synthesis, pp. 119–124 (2005)
Tao, M.W., Johnson, M.K., Paris, S.: Error-tolerant image compositing. Int. J. Comput. Vis. 103, 178–189 (2013)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Proceedings of IEEE ICCV, pp. 839–846 (1998)
Vese, L.A., Osher, S.: Modeling textures with total variation minimization and oscillating patterns in image processing. J. Sci. Comput. 19, 553–572 (2003)
Wang, Y., Yang, J., Yin, W., Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Imaging Sci. 1, 248–272 (2008)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error measurement to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)
Weickert, J.: Anisotropic Diffusion in Image Processing. Teubner, Leipzig (1998)
Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via \(L_0\) gradient minimization. ACM Trans. Graph. 30, 174:1–174:12 (2011)
Zhuo, S., Guo, D., Sim, T.: Robust flash deblurring. In: Proceedings of CVPR IEEE, pp. 2440–2447 (2010)
Acknowledgments
Myungjoo Kang and Seungmi Oh were supported by the Basic Science Research Program(2014-011269) through the National Research Foundation of Korea and the Development Program (10040409) funded by the Ministry of Knowledge Economy (MKE, Korea).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Oh, S., Kang, M. Image Decomposition using a Local Gradient Constraint. J Sci Comput 63, 213–232 (2015). https://doi.org/10.1007/s10915-014-9889-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10915-014-9889-y