×

A novel Euler’s elastica-based segmentation approach for noisy images using the progressive hedging algorithm. (English) Zbl 1455.94036

Summary: Euler’s elastica-based unsupervised segmentation models have strong capability of completing the missing boundaries for existing objects in a clean image, but they are not working well for noisy images. This paper aims to establish a Euler’s elastica-based approach that can properly deal with the random noises to improve the segmentation performance for noisy images. The corresponding formulation of stochastic optimization is solved via the progressive hedging algorithm (PHA), and the description of each individual scenario is obtained by the alternating direction method of multipliers. Technically, all the sub-problems derived from the framework of PHA can be solved by using the curvature-weighted approach and the convex relaxation method. Then, an alternating optimization strategy is applied by using some powerful accelerating techniques including the fast Fourier transform and generalized soft threshold formulas. Extensive experiments have been conducted on both synthetic and real images, which displayed significant gains of the proposed segmentation models and demonstrated the advantages of the developed algorithms.

MSC:

94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
68U10 Computing methodologies for image processing
90C15 Stochastic programming
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] Mumford, D.; Shah, J., Optimal approximations by piecewise smooth functions and associated variational problems, Commun. Pure Appl. Math., 42, 5, 577-685 (1989) · Zbl 0691.49036
[2] Chan, Tf; Vese, La, Active contours without edges, IEEE Trans. Image Process., 10, 2, 266-277 (2001) · Zbl 1039.68779
[3] Li, F., A multiphase image segmentation method based on fuzzy region competition, SIAM J. Imaging Sci., 3, 3, 277-299 (2010) · Zbl 1200.68267
[4] Yu, H.; Wang, Ww; Feng, Xc, A new fast multiphase image segmentation algorithm based on nonconvex regularizer, Pattern Recognit., 45, 1, 363-372 (2012) · Zbl 1225.68260
[5] Wang, B.; Yuan, X.; Gao, X., A hybrid level set with semantic shape constraint for object segmentation, IEEE Trans. Cybern., 49, 1558-1569 (2018)
[6] Tan, L.; Pan, Z.; Liu, W.; Duan, J.; Wei, W.; Wang, G., Image segmentation with depth information via simplified variational level set formulation, J. Math. Imaging Vis., 60, 1, 1-17 (2018) · Zbl 1387.94024
[7] Zhu, W.; Chan, Tf; Esedoglu, S., Segmentation with depth: a level set approach, SIAM J. Sci. Comput., 28, 5, 1957-1973 (2006) · Zbl 1344.68266
[8] Tan, L.; Liu, W.; Li, L., A fast computational approach for illusory contour reconstruction, Multimed. Tools Appl., 78, 8, 10449-10472 (2019)
[9] Vese, La; Chan, Tf, A multiphase level set framework for image segmentation using the Mumford and Shah model, Int. J. Comput. Vis., 50, 3, 271-293 (2002) · Zbl 1012.68782
[10] Paragios, N.; Deriche, R., Geodesic active regions: a new framework to deal with frame partition problems in computer vision, J. Vis. Commun. Image Represent., 13, 1-2, 249-268 (2002)
[11] Martin, P.; Réfrégier, P.; Goudail, F.; Guérault, F., Influence of the noise model on level set active contour segmentation, IEEE Trans. Pattern Anal. Mach. Intell., 26, 799-803 (2004)
[12] Sawatzky, A., A variational framework for region-based segmentation incorporating physical noise models, J. Math. Imaging Vis., 47, 3, 179-209 (2013) · Zbl 1291.68402
[13] Zhu, W.; Tai, Xc; Chan, Tf, Image segmentation using Euler’s elastica as the regularization, J. Sci. Comput., 57, 2, 414-438 (2013) · Zbl 1282.65037
[14] Tai, Xc; Duan, Jm, A simple fast algorithm for minimization of the elasitica energy combining binary and level set representations, Int. J. Numer. Anal. Model., 14, 6, 809-821 (2017) · Zbl 1378.65133
[15] Nitzberg, M.; Mumford, D.; Shiota, T., Filtering, Segmentation, and Depth, Lecture Notesin Computer Sciences, 662 (1993), Berlin: Springer, Berlin · Zbl 0801.68171
[16] Kang, Sh; Zhu, W.; Shen, Jh, Illusory shapes via corner fusion, SIAM J. Imaging Sci., 7, 4, 1907-1936 (2014) · Zbl 1320.68217
[17] Zhu, W.; Tai, Xc; Chan, Tf, Augmented Lagrangian method for a mean curvature based image denoising model, Inverse Problems Imaging, 7, 4, 1409-1432 (2013) · Zbl 1311.94015
[18] Tan, L.; Liu, W.; Pan, Z., Color image restoration and inpainting via multi-channel total curvature, Appl. Math. Model., 61, 280-299 (2018) · Zbl 1460.94014
[19] Tan, L.; Liang, A.; Li, L., Automatic prostate segmentation based on fusion between deep network and variational methods, J. X-ray Sci. Technol. (2019)
[20] Yashtini, M.; Kang, Sh, A fast relaxed normal two split method and an effective weighted tv approach for Euler’s elastica image inpainting, SIAM J. Imaging Sci., 9, 4, 1552-1581 (2016) · Zbl 1366.94075
[21] Yan, Y.; Nie, F.; Li, W., Image classification by cross-media active learning with privileged information, IEEE Trans. Multimed., 18, 12, 2494-2502 (2016)
[22] Rockafellar, Rt; Wets, Rjb, Stochastic variational inequalities: single-stage to multistage, Math. Program., 165, 1, 331-360 (2017) · Zbl 1378.49010
[23] Rockafellar, Rt; Sun, J., Solving monotone stochastic variational inequalities and complementarity problems by progressive hedging, Math. Program., 174, 453-471 (2019) · Zbl 1421.90100
[24] Glowinski, R.; Pan, Tw; Tai, Xc, Some Facts About Operator-splitting and Alternating Direction Methods, 19-94 (2016), Cham: Springer, Cham · Zbl 1372.65205
[25] Bae, E.; Shi, J.; Tai, Xc, Graph cuts for curvature based image denoising, IEEE Trans. Image Process., 20, 5, 1199-1210 (2011) · Zbl 1372.94015
[26] Deng, L.J., Glowinski, R., Tai, X.C.: A New Operator Splitting Method for Euler’s Elastica Model. arXiv preprint arXiv:1811.07091 (2018)
[27] Morel, Jm; Petro, Ab; Sbert, C., Screened Poisson equation for image contrast enhancement, Image Process. Line, 4, 16-29 (2014)
[28] Kellman, P., Classification images reveal that deep learning networks fail to perceive illusory contours, J. Vis., 17, 10, 569-569 (2017)
[29] Poscoliero, T.; Girelli, M., Electrophysiological modulation in an effort to complete illusory figures: configuration, illusory contour and closure effects, Brain Topogr., 31, 2, 202-217 (2018)
[30] Rockafellar, Rt; Wets, Rj-B, Scenarios and policy aggregation in optimization under uncertainty, Math. Oper. Res., 16, 119-147 (1991) · Zbl 0729.90067
[31] Sun, J.; Xu, Hl; Zhang, M., A new interpretation of the progressive hedging algorithm for multistage stochastic minimization problems, J. Ind. Manag. Optim., 2, 1-2 (2019)
[32] Chan, Tf; Sandberg, By; Vese, La, Active contours without edges for vector-valued images, J. Vis. Commun. Image Represent., 11, 2, 130-141 (2000)
[33] Rudin, L.; Osher, S.; Fatemi, E., Nonlinear total variation based noise removal algorithms, Phys. D Nonlinear Phenom., 60, 1-4, 259-268 (1992) · Zbl 0780.49028
[34] Chan, Tf; Esedoglu, S.; Nikolova, M., Algorithms for finding global minimizers of image segmentation and denoising models, SIAM J. Appl. Math., 66, 5, 1632-1648 (2006) · Zbl 1117.94002
[35] Yuan, J., Bae, E., Tai, X.C.: A Study on Continuous Max-Flow and Min-Cut Approaches. In:CVPR, USA, San Francisco (2010)
[36] Bae, E., A Fast Continuous Max-Flow Approach to Non-convex Multi-labeling Problems, 134-154 (2014), Berlin: Springer, Berlin
[37] Hong, M.; Luo, Zq, On the linear convergence of the alternating direction method of multipliers, Math. Program., 162, 1-2, 165-199 (2017) · Zbl 1362.90313
[38] Liu, Q., Shen, X., Gu, Y.: Linearized ADMM for Non-convex Non-smooth Optimization with Convergence Analysis. arXiv preprint arXiv:1705.02502 (2017)
[39] Myllykoski, M.; Glowinski, R.; Karkkainen, T.; Rossi, T., A new augmented Lagrangian approach for L1-mean curvature image denoising, SIAM J. Imaging Sci., 8, 1, 95-125 (2015) · Zbl 1330.94011
[40] Yashtini, M., Alternating Direction Method of Multiplier for Euler’s Elastica-Based Denoising, Scale Space and Variational Methods in Computer Vision, 690-701 (2015), Berlin: Springer, Berlin · Zbl 1444.94026
[41] Bae, E.; Tai, Xc; Zhu, W., Augmented Lagrangian method for an Euler’s elastica based segmentation model that promotes convex contours, Inverse Problems Imaging, 11, 1, 1-23 (2017) · Zbl 1416.94013
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.