Abstract
Decomposing multidimensional signals, such as images, into spatially compact, potentially overlapping modes of essentially wavelike nature makes these components accessible for further downstream analysis. This decomposition enables space–frequency analysis, demodulation, estimation of local orientation, edge and corner detection, texture analysis, denoising, inpainting, or curvature estimation. Our model decomposes the input signal into modes with narrow Fourier bandwidth; to cope with sharp region boundaries, incompatible with narrow bandwidth, we introduce binary support functions that act as masks on the narrow-band mode for image recomposition. \(L^1\) and TV terms promote sparsity and spatial compactness. Constraining the support functions to partitions of the signal domain, we effectively get an image segmentation model based on spectral homogeneity. By coupling several submodes together with a single support function, we are able to decompose an image into several crystal grains. Our efficient algorithm is based on variable splitting and alternate direction optimization; we employ Merriman–Bence–Osher-like threshold dynamics to handle efficiently the motion by mean curvature of the support function boundaries under the sparsity promoting terms. The versatility and effectiveness of our proposed model is demonstrated on a broad variety of example images from different modalities. These demonstrations include the decomposition of images into overlapping modes with smooth or sharp boundaries, segmentation of images of crystal grains, and inpainting of damaged image regions through artifact detection.
Similar content being viewed by others
Notes
Throughout this paper, we will be using notation pertaining to images defined over continuous domains, albeit it is implicitly understood that numerical implementations will always make use of appropriate commonplace discretization and quantization.
Similarly, in higher dimensions, a half-space of the frequency domain needs to be suppressed.
To be more precise, the objective is convex in \({\mathbf {\upomega }}_k\) if we consider the analytic signal construction for \(u_{AS,k}\) fixed while optimizing for \({\mathbf {\upomega }}_k\).
Note that the spectrum of \(u_k\) is complex-valued, so the process of “taking the first variation” is not self-evident. However, the functional is analytic in \({\hat{u}}_k\) and complex-valued equivalents to the standard derivatives do indeed apply.
Again we omit iteration superscripts for \(A_i\), but it is understood that we always use the most recent estimate of a variable, \(A_i^{t+1}\) for \(i<k\) and \(A_i^t\) for \(i>k\).
Here, t is understood as an artificial time introduced for the sole purpose of differential equation notation, but quantized into the discrete iterates of the scheme.
Of course, the simpler 2D-VMD model only uses a subset of these parameters, for the support functions are fixed at \(A_k=1\) uniformly.
MATLAB code available at http://bigwww.epfl.ch/demo/steerable-wavelets/.
Obfuscated MATLAB p-code available at http://perso.ens-lyon.fr/nelly.pustelnik/Software/Toolbox_PHT_2D_v1.0.zip.
Lower artifact threshold \(\delta \) and higher TV weight \({\gamma }_k\) might increase the mode cleanliness even further.
Image used with permission, courtesy by Richard Wheeler, Sir William Dunn School of Pathology, University of Oxford, UK.
Ibid.
References
Ayvaci, A., Raptis, M., Soatto, S.: Sparse occlusion detection with optical flow. Int. J. Comput. Vis. 97(3), 322–338 (2011). doi:10.1007/s11263-011-0490-7
Bertsekas, D.P.: Multiplier methods: a survey. Automatica 12(2), 133–145 (1976)
Bonnell, D.A., Basov, D.N., Bode, M., Diebold, U., Kalinin, S.V., Madhavan, V., Novotny, L., Salmeron, M., Schwarz, U.D., Weiss, P.S.: Imaging physical phenomena with local probes: from electrons to photons. Rev. Mod. Phys. 84(3), 1343–1381 (2012). doi:10.1103/RevModPhys.84.1343
Bülow, T., Sommer, G.: A novel approach to the 2D analytic signal. In: Computer Analysis of Images and Patterns, pp. 25–32 (1999)
Candes, E.J., Donoho, D.L.: Curvelets: A surprisingly effective nonadaptive representation for objects with edges. In: Curve and Surface Fitting, pp. 105–120 (1999)
Carson, J.: Notes on the theory of modulation. Proc. IRE 10(1), 57–64 (1922). doi:10.1109/JRPROC.1922.219793
Chambolle, A.: An algorithm for total variation minimization and applications. J. Math. Imaging Vis. 20, 89–97 (2004)
Claridge, S.A., Schwartz, J.J., Weiss, P.S.: Electrons, photons, and force: quantitative single-molecule measurements from physics to biology. ACS Nano 5(2), 693–729 (2011). doi:10.1021/nn103298x
Clausel, M., Oberlin, T., Perrier, V.: The monogenic synchrosqueezed wavelet transform: a tool for the decomposition/demodulation of AM-FM images (2012). arxiv:1211.5082
Claridge, S.A., Thomas, J.C., Silverman, M.A., Schwartz, J.J., Yang, Y., Wang, C., Weiss, P.S.: Differentiating amino acid residues and side chain orientations in peptides using scanning tunneling microscopy. J. Am. Chem. Soc. 135(49), 18528–18535 (2013). doi:10.1021/ja408550a
Cohen, L.D.: Auxiliary variables and two-step iterative algorithms in computer vision problems. J. Math. Imaging Vis. 6(1), 59–83 (1996). doi:10.1007/BF00127375
Combettes, P.L., Pesquet, J.C.: Proximal splitting methods in signal processing. In: Bauschke, H.H., Burachik, R.S., Combettes, P.L., Elser, V., Luke, D.R., Wolkowicz, H. (eds.) Fixed-Point Algorithms for Inverse Problems in Science and Engineering, Springer Optimization and Its Applications, vol. 49, pp. 185–212. Springer, New York, NY (2011). doi:10.1007/978-1-4419-9569-8
Daubechies, I.: Orthonormal bases of compactly supported wavelets. Commun. Pure Appl. Math. 41(7), 909–996 (1988). doi:10.1002/cpa.3160410705
Daubechies, I., Lu, J., Wu, H.T.: Synchrosqueezed wavelet transforms: an empirical mode decomposition-like tool. Appl. Comput. Harmonic Anal. 30(2), 243–261 (2011). doi:10.1016/j.acha.2010.08.002
Do, M., Vetterli, M.: Pyramidal directional filter banks and curvelets. In: Proceedings 2001 International Conference on Image Processing, vol. 2, pp. 158–161. IEEE (2001). doi:10.1109/ICIP.2001.958075
Dong, W., Li, X., Lin, X., Li, Z.: A bidimensional empirical mode decomposition method for fusion of multispectral and panchromatic remote sensing images. Remote Sens. 6(9), 8446–8467 (2014). doi:10.3390/rs6098446
Dragomiretskiy, K., Zosso, D.: Variational mode decomposition. IEEE Trans. Signal Process. 62(3), 531–544 (2014). doi:10.1109/TSP.2013.2288675
Dragomiretskiy, K., Zosso, D.: Two-dimensional variational mode decomposition. In: Tai, X.C., Bae, E., Chan, T.F., Lysaker, M. (eds.) EMMCVPR 2015. Lecture Notes in Computer Science, vol. 8932, pp. 197–208. Springer, Berlin (2015). doi:10.1007/978-3-319-14612-6_15
Elsey, M., Wirth, B.: Fast automated detection of crystal distortion and crystal defects in polycrystal images. Multiscale Model. Simul. 12(1), 1–24. doi:10.1137/130916515
Esedoglu, S., Otto, F.: Threshold dynamics for networks with arbitrary surface tensions. Commun. Pure Appl. Math. 68(5), 808–864 (2015). doi:10.1002/cpa.21527
Esedoglu, S., Tsai, Y.H.R.: Threshold dynamics for the piecewise constant Mumford–Shah functional. J. Comput. Phys. 211, 367–384 (2006). doi:10.1016/j.jcp.2005.05.027
Estellers, V., Zosso, D., Bresson, X., Thiran, J.P.: Harmonic active contours. IEEE Trans. Image Process. 23(1), 69–82 (2014). doi:10.1109/TIP.2013.2286326
Fauchereau, N., Pegram, G.G.S., Sinclair, S.: Empirical mode decomposition on the sphere: application to the spatial scales of surface temperature variations. Hydrol. Earth Syst. Sci. 12(3), 933–941 (2008). doi:10.5194/hess-12-933-2008
Flandrin, P., Gonçalvès, P., Rilling, G.: EMD equivalent filter banks, from interpretation to applications. In: Hilbert–Huang Transform and Its Applications, pp. 57–74 (2005)
Gabor, D.: Theory of communication. J. Inst. Electr. Eng. Part III Radio Commun. Eng. 93(26), 429–457 (1946)
Garcia-Cardona, C., Merkurjev, E., Bertozzi, A.L., Flenner, A., Percus, A.G.: Multiclass data segmentation using diffuse interface methods on graphs. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1600–1613 (2014). doi:10.1109/TPAMI.2014.2300478
Georgoulas, G., Loutas, T., Stylios, C.D., Kostopoulos, V.: Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition. Mech. Syst. Signal Process. 41(1–2), 510–525 (2013). doi:10.1016/j.ymssp.2013.02.020
Gilles, J.: Multiscale texture separation. Multiscale Model. Simul. 10(4), 1409–1427 (2012). doi:10.1137/120881579
Gilles, J.: Empirical wavelet transform. IEEE Trans. Signal Process. 61(16), 3999–4010 (2013). doi:10.1109/TSP.2013.2265222
Gilles, J., Tran, G., Osher, S.: 2D empirical transforms. Wavelets, ridgelets, and curvelets revisited. SIAM J. Imaging Sci. 7(1), 157–186 (2014). doi:10.1137/130923774
Glowinski, R., Le Tallec, P.: Augmented Lagrangian and Operator-Splitting Methods in Nonlinear Mechanics. Society for Industrial and Applied Mathematics (SIAM), Philadelphia (1989)
Goldstein, T., Osher, S.: The split Bregman method for L1-regularized problems. SIAM J. Imaging Sci. 2(2), 323–343 (2009). doi:10.1137/080725891
Grafakos, L.: Classical Fourier Analysis, Graduate Texts in Mathematics, vol. 249. Springer, New York, NY (2009). doi:10.1007/978-0-387-09432-8
Guo, K., Labate, D.: Optimally sparse multidimensional representation using shearlets. SIAM J. Math. Anal. 39(1), 298–318 (2007). doi:10.1137/060649781
Han, J., van der Baan, M.: Empirical mode decomposition for seismic time-frequency analysis. Geophysics 78(2), O9–O19 (2013). doi:10.1190/geo2012-0199.1
Han, P., Kurland, A.R., Giordano, A.N., Nanayakkara, S.U., Blake, M.M., Pochas, C.M., Weiss, P.S.: Heads and tails: simultaneous exposed and buried interface imaging of monolayers. ACS Nano 3(10), 3115–3121 (2009). doi:10.1021/nn901030x
Hestenes, M.R.: Multiplier and gradient methods. J. Optim. Theory Appl. 4(5), 303–320 (1969)
Hou, T.Y., Shi, Z.: Adaptive data analysis via sparse time-frequency representation. Adv. Adapt. Data Anal. 03(1 & 2), 1–28 (2011). doi:10.1142/S1793536911000647
Hou, T.Y., Shi, Z.: Data-driven time frequency analysis. Appl. Comput. Harmonic Anal. 35(2), 284–308 (2013). doi:10.1016/j.acha.2012.10.001
Hou, T.Y., Shi, Z.: Sparse time-frequency decomposition for multiple signals with same frequencies (2015). arXiv:1507.02037
Hu, M., Liang, H.: Intrinsic mode entropy based on multivariate empirical mode decomposition and its application to neural data analysis. Cogn. Neurodyn. 5(3), 277–284 (2011). doi:10.1007/s11571-011-9159-8
Hu, H., Sunu, J., Bertozzi, A.L.: Multi-class graph Mumford–Shah model for plume detection using the MBO scheme. In: Tai, X.C., Bae, E., Chan, T.F., Lysaker, M. (eds.) Energy Minimization Methods in Computer Vision and Pattern Recognition, Lecture Notes in Computer Science, vol. 8932, pp. 209–222. Springer, Berlin (2015). doi:10.1007/978-3-319-14612-6_16
Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.C., Tung, C.C., Liu, H.H.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. A Math. Phys. Eng. Sci. 454(1971), 903–995 (1998). doi:10.1098/rspa.1998.0193
Labate, D., Lim, W.Q., Kutyniok, G., Weiss, G.: Sparse multidimensional representation using shearlets. In: Papadakis, M., Laine, A.F., Unser, M.A. (eds.) Optics and Photonics 2005, pp. 1–9. International Society for Optics and Photonics, Bellingham (2005). doi:10.1117/12.613494
Lee, T.S.: Image representation using 2D Gabor wavelets. IEEE Trans. Pattern Anal. Mach. Intell. 18(10), 959–971 (1996). doi:10.1109/34.541406
Leo, M., Piccolo, R., Distante, C., Memmolo, P., Paturzo, M., Ferraro, P.: Multilevel bidimensional empirical mode decomposition: a new speckle reduction method in digital holography. Opt. Eng. 53(11), 112,314 (2014). doi:10.1117/1.OE.53.11.112314
Mallat, S.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11(7), 674–693 (1989). doi:10.1109/34.192463
Meignen, S., Perrier, V.: A new formulation for empirical mode decomposition based on constrained optimization. IEEE Signal Process. Lett. 14(12), 932–935 (2007). doi:10.1109/LSP.2007.904706
Merkurjev, E., Garcia-Cardona, C., Bertozzi, A.L., Flenner, A., Percus, A.G.: Diffuse interface methods for multiclass segmentation of high-dimensional data. Appl. Math. Lett. 33, 29–34 (2014). doi:10.1016/j.aml.2014.02.008
Merriman, B., Bence, J.K., Osher, S.J.: Motion of multiple junctions: a level set approach. J. Comput. Phys. 112(2), 334–363 (1994). doi:10.1006/jcph.1994.1105
Moore, A.M., Yeganeh, S., Yao, Y., Claridge, S.A., Tour, J.M., Ratner, M.A., Weiss, P.S.: Polarizabilities of adsorbed and assembled molecules: measuring the conductance through buried contacts. ACS Nano 4(12), 7630–7636 (2010). doi:10.1021/nn102371z
Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer, Berlin (2006)
Nunes, J., Bouaoune, Y., Delechelle, E., Niang, O., Bunel, P.: Image analysis by bidimensional empirical mode decomposition. Image Vis. Comput. 21(12), 1019–1026 (2003). doi:10.1016/S0262-8856(03)00094-5
Rilling, G., Flandrin, P.: One or two frequencies? The empirical mode decomposition answers. IEEE Trans. Signal Process. 56(1), 85–95 (2008). doi:10.1109/TSP.2007.906771
Rilling, G., Flandrin, P.: Sampling effects on the empirical mode decomposition. Adv. Adapt. Data Anal. 01(01), 43–59 (2009). doi:10.1142/S1793536909000023
Rilling, G., Flandrin, P., Gonçalvès, P.: On empirical mode decomposition and its algorithms. In: IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing (2003)
Rockafellar, R.T.: A dual approach to solving nonlinear programming problems by unconstrained optimization. Math. Program. 5(1), 354–373 (1973). doi:10.1007/BF01580138
Ruuth, S.: Efficient algorithms for diffusion-generated motion by mean curvature. J. Comput. Phys. 625, 603–625 (1998). doi:10.1006/jcph.1998.6025
Schmitt, J., Pustelnik, N., Borgnat, P., Flandrin, P., Condat, L.: 2-D Prony-Huang Transform: A New Tool for 2-D Spectral Analysis, p. 24 (2014). arxiv:1404.7680
Schmitt, J., Pustelnik, N., Borgnat, P., Flandrin, P., Condat, L.: 2D Prony–Huang transform: a new tool for 2D spectral analysis. IEEE Trans. Image Process. 23(12), 5233–5248 (2014). doi:10.1109/TIP.2014.2363000
Sharpley, R.C., Vatchev, V.: Analysis of the intrinsic mode functions. Constr. Approx. 24(1), 17–47 (2005). doi:10.1007/s00365-005-0603-z
Strikwerda, J.C.: Finite Difference Schemes and Partial Differential Equations, 2nd edn. SIAM, Philadelphia (2004)
Sykes, E.C.H., Mantooth, B.A., Han, P., Donhauser, Z.J., Weiss, P.S.: Substrate-mediated intermolecular interactions: a quantitative single molecule analysis. J. Am. Chem. Soc. 127(19), 7255–7260 (2005). doi:10.1021/ja0472331
Szuts, Z.B., Blundell, J.R., Chidichimo, M.P., Marotzke, J.: A vertical-mode decomposition to investigate low-frequency internal motion across the Atlantic at \(26^{\circ }\) N. Ocean Sci. 8(3), 345–367 (2012). doi:10.5194/os-8-345-2012
Tang, J., Zhao, L., Yue, H., Yu, W., Chai, T.: Vibration analysis based on empirical mode decomposition and partial least square. Proc. Eng. 16, 646–652 (2011). doi:10.1016/j.proeng.2011.08.1136
Tavallali, P., Hou, T.Y., Shi, Z.: Extraction of intrawave signals using the sparse time-frequency representation method. Multiscale Model. Simul. 12(4), 1458–1493 (2014). doi:10.1137/140957767
Thomas, J.C., Schwartz, J.J., Hohman, J.N., Claridge, S.A., Auluck, H.S., Serino, A.C., Spokoyny, A.M., Tran, G., Kelly, K.F., Mirkin, C.A., Gilles, J., Osher, S.J., Weiss, P.S.: Defect-tolerant aligned dipoles within two-dimensional plastic lattices. ACS Nano 9(5), 4734–4742 (2015). doi:10.1021/acsnano.5b01329
Thomas, J.C., Goronzy, D.P., Dragomiretskiy, K., Zosso, D., Gilles, J., Osher, S.J., Bertozzi, A.L., Weiss, P.S.: Mapping buried hydrogen-bonding networks. ACS Nano 10(5), 5446–5451 (2016). doi:10.1021/acsnano.6b01717
Unser, M., Sage, D., Van De Ville, D.: Multiresolution monogenic signal analysis using the Riesz–Laplace wavelet transform. IEEE Trans. Image Process. 18(11), 2402–2418 (2009). doi:10.1109/TIP.2009.2027628
Unser, M., Chenouard, N., Van De Ville, D.: Steerable pyramids and tight wavelet frames in \(L_{2}(\mathbb{R}^d)\). IEEE Trans. Image Process. 20(10), 2705–2721 (2011). doi:10.1109/TIP.2011.2138147
Wu, Z., Huang, N.E.: Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv. Adapt. Data Anal. 01(01), 1–41 (2009). doi:10.1142/S1793536909000047
Wu, H.T., Flandrin, P., Daubechies, I.: One or two frequencies? The synchrosqueezing answers. Adv. Adapt. Data Anal. 03(01n02), 29–39 (2011). doi:10.1142/S179353691100074X
Yan, M.: Restoration of images corrupted by impulse noise and mixed Gaussian impulse noise using blind inpainting. SIAM J. Imaging Sci. 6(3), 1227–1245 (2013). doi:10.1137/12087178X
Yang, H., Ying, L.: Synchrosqueezed wave packet transform for 2D mode decomposition. SIAM J. Imaging Sci. 6(4), 1979–2009 (2013). doi:10.1137/120891113
Yang, H., Lu, J., Ying, L.: Crystal image analysis using 2D synchrosqueezed transforms, p. 27 (2014). arxiv:1402.1262
Yugay, D., Goronzy, D.P., Kawakami, L.M., Claridge, S.A., Song, T.B., Yan, Z., Xie, Y.H., Gilles, J., Yang, Y., Weiss, P.S.: Copper ion binding site in \(\beta \)-amyloid peptide. Nano Lett. 16(10), 6282–6289 (2016). doi:10.1021/acs.nanolett.6b02590
Zhu, M., Wright, S.J., Chan, T.F.: Duality-based algorithms for total-variation-regularized image restoration. Comput. Optim. Appl. 47(3), 377–400 (2010). doi:10.1007/s10589-008-9225-2
Zosso, D., An, J., Stevick, J., Takaki, N., Weiss, M., Slaughter, L.S., Cao, H.H., Weiss, P.S., Bertozzi, A.L.: Image segmentation with dynamic artifacts detection and bias correction. AIMS Journal of Inverse Problems Imaging, p. 24 (2017) (accepted)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the Swiss National Science Foundation (SNF) under Grants PBELP2-137727 and P300P2-147778, the UC Lab Fees Research Grant 12-LR-236660, and the W. M. Keck Foundation.
Rights and permissions
About this article
Cite this article
Zosso, D., Dragomiretskiy, K., Bertozzi, A.L. et al. Two-Dimensional Compact Variational Mode Decomposition. J Math Imaging Vis 58, 294–320 (2017). https://doi.org/10.1007/s10851-017-0710-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-017-0710-z
Keywords
- Image decomposition
- Image segmentation
- Spatio-spectral decomposition
- Microscopy
- Crystal grains
- Artifact detection
- Threshold dynamics
- Variational methods
- Sparse time–frequency analysis