Abstract
The total variation (TV) regularization model for image restoration is widely utilized due to its edge preservation properties. Despite its advantages, the TV regularization can obtain spurious oscillations in flat regions of digital images and thus recent works advocate high-order TV regularization models. In this work, we propose an adaptive image restoration method based on a combination of first-order and second-order total variations regularization with an inverse-gradient-based adaptive parameter. The proposed model removes noise effectively and preserves image structures. Due to the adaptive parameter estimation based on the inverse gradient, it avoids the staircasing artifacts associated with TV regularization and its variant models. Experimental results indicate that the proposed method obtains better restorations in terms of visual quality as well as quantitatively. In particular, our proposed adaptive higher-order TV method obtained (19.3159, 0.7172, 0.90985, 0.79934, 0.99838) PSNR, SSIM, MS-SSIM, F-SIM, and P-SIM values compared to related models such as the TV-Bounded Hessian (18.9735, 0.6599, 0.8718, 0.73833, 0.99767), and TV-Laplacian (19.0345, 0.6719, 0.88198, 0.75405, 0.99789).
Similar content being viewed by others
References
Cheng, J., Gao, Y., Guo, B., Zuo, W.: Image restoration using spatially variant hyper-Laplacian prior. Signal Image Video Process 13(1), 155–162 (2019)
Prasath, V.B.S., Vorotnikov, D., Pelapur, R., Jose, S., Seetharaman, G., Palaniappan, K.: Multiscale Tikhonov-total variation image restoration using spatially varying edge coherence exponent. IEEE Trans. Image Process. 24(12), 5220–5235 (2015)
Chan, T.F., Shen, J.: Image Processing and Analysis: Variational, PDE, Wavelet and Stochastic Methods. SIAM, New York (2005)
Thanh, D.N.H., Dvoenko, S.: A variational method to remove the combination of poisson and Gaussian noises. In: 5th International Workshop on Image Mining: Theory and Applications, pp. 38–45, Germany (2015)
Shi, Y., Wang, K., Chen, C., Xu, L., Lin, L.: Structure-preserving image super-resolution via contextualized multitask learning. IEEE Trans. Multimedia. 19(12), 2804–2815 (2017). https://doi.org/10.1109/TMM.2017.2711263
Liu, L., Pang, Z.-F., Duan, Y.: Retinex based on exponent-type total variation scheme. Inverse Prob. Imaging. 12(5), 1199–1217 (2018). https://doi.org/10.3934/ipi.2018050
Liu, P., Zhang, H., Zhang, K., Lin, L., Zuo, W.: Multi-level wavelet-CNN for image restoration. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Salt Lake city (2018). https://doi.org/10.1109/CVPRW.2018.00121
Fu, B., Li, Y., Wang, X.-H., Ren, Y.-G.: Image super-resolution using TV priori guided convolutional network. Pattern Recogn. Lett. 125, 780–784 (2019). https://doi.org/10.1016/j.patrec.2019.06.022
Thanh, D.N.H., Prasath, V.B.S., Hieu, L.M.: A review on CT and X-ray images denoising methods. Informatica 43(2), 151–159 (2019)
Thanh, D.N.H., Dvoenko, S.: Image noise removal based on total variation. Comput. Opt. 39(4), 564–571 (2015)
Prasath, V.B.S.: Quantum noise removal in X-ray images with adaptive total variation regularization. Informatica 28(3), 505–515 (2017)
Thanh, D.N.H., Dvoenko, S.: A method of total variation to remove the mixed Poisson–Gaussian noise. Pattern Rec. Image Ana. 26(2), 285–293 (2016)
Mamaev, N.V., Yurin, D.V., Krylov, A.S.: Finding the parameters of a nonlinear diffusion denoising method by ridge analysis. Comput. Math. Model. 29, 334–343 (2018). https://doi.org/10.1007/s10598-018-9413-6
Dovganich, A.A., Krylov, A.S.: A nonlocal image denoising algorithm using the structural similarity metric. Program. Comput. Soft. 45, 141–146 (2019). https://doi.org/10.1134/S0361768819040029
Pang, Z.-F., Zhang, H.-L., Luo, S., Zeng, T.: Image denoising based on the adaptive weighted TVp regularization. Signal Process. 167, 107325 (2020). https://doi.org/10.1016/j.sigpro.2019.107325
Teoh, S.H., Ibrahim, H.: Robust algorithm for broad impulse noise removal utilizing intensity distance and intensity height methodologies. SIViP 8, 223–242 (2014). https://doi.org/10.1007/s11760-013-0538-y
Erkan, U., Enginoglu, S., Thanh, D.N.H., Hieu, L.M.: Adaptive frequency median filter for the salt-and-pepper denoising problem. IET Image Process. (2019). https://doi.org/10.1049/iet-ipr.2019.0398
Chen, Y., et al.: Structure-adaptive fuzzy estimation for random-valued impulse noise suppression. IEEE. Trans. Circ. Syst. Video Technol. 28(2), 414–427 (2018). https://doi.org/10.1109/TCSVT.2016.2615444
Hsieh, P.-W., Shao, P.-C., Yang, S.-Y.: A regularization model with adaptive diffusivity for variational image denoising. Signal Process. 149, 214–228 (2018). https://doi.org/10.1016/j.sigpro.2017.12.011
Erkan, U., Thanh, D.N.H., Hieu, L.M., Enginoglu, S.: An iterative mean filter for image denoising. IEEE Access. 7, 167847–167859 (2019). https://doi.org/10.1109/ACCESS.2019.2953924
Almeida, M., Almeida, L.: Blind and semi-blind deblurring of natural images. IEEE Trans. Image Process. 19(1), 36–52 (2009)
Abbass, M., Kim, H., Abdelwahab, S., Haggag, S., El-Rabaie, E., Dessouky, M., El-Samie, F.: Image deconvolution using homomorphic technique. Signal Image Video Process. 13(4), 703–709 (2019)
Thanh, D.N.H., Prasath, V.B.S., Son, N.V., Hieu, L.M.: An adaptive image inpainting method based on the modified Mumford–Shah model and multiscale parameter estimation. Comput. Opt. 42(6), 251–257 (2018)
Mirkamali, M., Nagabhushan, P.: Object removal by depth-wise image inpainting. Signal Image Video Process. 9(8), 1785–1794 (2015)
Wang, W., Yuan, X.: Recent advances in image dehazing. IEEE/CAA J Automatica Sinica 4(3), 410–436 (2017)
Grigoras, R., Ciocoiu, I.B.: Comparative analysis of deraining algorithms. In: International Symposium on Signals, Circuits and Systems, Romania (2017)
Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1990)
Papafitsoros, K., Schönlieb, C.: A combined first and second order variational approach for image reconstruction. J Math. Imag. Vis. 48(2), 308–338 (2014)
Arbelaez, P., Fowlkes, C., Martin, D.: The Berkeley Segmentation Dataset (BSDS). https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/. Accessed 10/12/2018
Chan, R., Liang, H., Wei, S., Nikolova, M., Tai, X.: High-order total variation regularization approach for axially symmetric object tomography from a single radiograph. Inverse Prob. Imag. 9(1), 55–77 (2015)
Lu, W., Duan, J., Qiu, Z., Pan, Z., Liu, R.W., Bai, L.: Implementation of high-order variational models made easy for image processing. Math. Meth. Appl. Sci. 39(14), 4208–4233 (2016)
Thanh, D.N.H., Thanh, L.T., Hien, N.N., Prasath, V.B.S.: Adaptive Total Variation L1 Regularization for Salt and Pepper Image Denoising. Optik-Int. J. Light Electron Opt. (2020). https://doi.org/10.1016/j.ijleo.2019.163677
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wang, Z., Simoncelli, E., Bovik, A.: Multi-scale structural similarity for image quality assessment. In: 37th IEEE Asilomar Conference on Signals, Systems and Computers, USA (2003)
Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20(8), 2378–2386 (2011)
Gu, K., Li, L., Lu, H., Min, X., Lin, W.: A fast reliable image quality predictor by fusing micro-and macro-structures. IEEE Trans. Ind. Electron. 64(5), 3903–3912 (2017)
Gu, K., Zhai, G., Lin, W., Yang, X., Zhang, W.: No-reference image sharpness assessment in autoregressive parameter space. IEEE Trans. Image Process. 24(10), 3218–3231 (2015)
Gu, K., Wang, S., Yang, H., Lin, W., Zhai, G., Yang, X., Zhang, W.: Saliency-guided quality assessment of screen content images. IEEE Trans. Multimed. 18(6), 1098–1110 (2016)
Gu, K., Qiao, J., Min, X., Yue, G., Lin, W., Thalmann, D.: Evaluating quality of screen content images via structural variation analysis. IEEE Trans. Vis. Comput. Graph. 24(10), 2689–2701 (2017)
Lu, W., Duan, J.: Higher order variational models (HOVM) for image processing. https://github.com/j-duan/HOVM. Accessed 10/12/2018
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Thanh, D.N.H., Prasath, V.S., Hieu, L.M. et al. An adaptive method for image restoration based on high-order total variation and inverse gradient. SIViP 14, 1189–1197 (2020). https://doi.org/10.1007/s11760-020-01657-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-020-01657-9