Abstract
By definition, an instance of image reconstruction often combines denoising, deblurring and enhancing objectively and appears as a fundamental process in visual processing systems which is mathematically an ill-posed inverse optimization problem. It suffers additional complexities because of a non-stationary nature of the image, restricting available methods to produce inconsistent restoration on a variety of image and degradation types. It requires filling this gap by a generic framework of image restoration. Therefore, in this paper, we modeled a novel data-driven framework of generic image reconstruction as a testing benchmark to the emerging application of deep learning. The proposed framework comprises of data engineering, image filtering and a regression neural network for better restoration of many degraded images. We evaluated the effectiveness of the framework on many images degraded by a Gaussian, out-of-focus, motion or airy-pattern blur and random additive white Gaussian noise. The performance appeared better in comparison to a benchmark and state-of-the-art generic image restoration results on several indicators. Furthermore, the framework performed better in comparison to a recent approach to image reconstruction which uses a deep convolutional neural network.
Similar content being viewed by others
Notes
Dataset website: http://archive.stsci.edu/cgi-bin/dss_form.
References
Marcus, G.: Deep Learning: A Critical Appraisal (Jan 2018). arXiv:1801.00631v1 [cs.AI]
Flamary, R.: Astronomical image reconstruction with convolutional neural networks. In: 25th European Signal Processing Conference (EUSIPCO), Kos, pp. 2468-2472. (2017). https://doi.org/10.23919/EUSIPCO.2017.8081654
Jin, K.H., McCann, M.T., Froustey, E., Unser, M.: Deep convolutional neural network for inverse problems in imaging. IEEE Trans. Image Process. 26(9), 4509–4522 (2017)
Biggs, D.S., Andrews, M.: Acceleration of iterative image restoration algorithms. Appl. Opt. 36(8), 1766–1775 (1997)
Hong, H., Hua, X., Zhang, X., et al.: Multi-frame real image restoration based on double loops with alternative maximum likelihood estimation. SIViP 10, 1489 (2016). https://doi.org/10.1007/s11760-016-0960-z
Hansen, P.C. et al.: Deblurring Images: Matrices, Spectra, and Filtering. Society of Industrial Appllied Mathematics, Philadelphia, PA 19104-2688 USA (2006)
Bilal, M., et al.: Optimal edge preserving restoration with efficient regularisation. Imaging Sci. J. 63(2), 68–75 (2015)
Kheradmand, A., Milanfar, P.: A general framework for regularized, similarity-based image restoration. IEEE Trans. Image Process. 24, 5136–5151 (2014)
Bilal, M., et al.: Novel optimization framework to recover true image data. Cognit. Comput. 7(6), 680–692 (2015)
Bilal, M., et al.: Modified particle swarm optimization and fuzzy regularization for pseudo de-convolution of spatially variant blurs. Multimed. Tools Appl. 75, 6533–6548 (2015). https://doi.org/10.1007/s11042-015-2587-4
Bilal, M., Wyne, M.F., Jaffar, M.A.: Image restoration by multivariate-stochastic optimization using improved particle swarm algorithm. In: Proceedings IEEE Congress Evolutionary Computation (CEC), pp. 2596–2603 (2016). https://doi.org/10.1007/s11042-015-2587-4
Perry, S.W.: Adaptive image restoration: perception based neural network models and algorithms, Ph.D. dissertation, School of Electrical and Information Engineering, Univ. Sydney, NSW, Australia (2006)
Xu, L., Ren, J., Liu, C., Jia, J.: Deep convolutional neural network for image deconvolution. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger,K.Q. (Eds.) Proceedings of the 27th International Conference on Neural Information Processing Systems, Volume 1 (NIPS’14), Vol. 1., pp. 1790-1798. MIT Press, Cambridge, MA, USA (Dec. 2014)
Pires, R., Santos, D., Souza, G., Levada, A., Papa, J.: A deep boltzmann machine-based approach for robust image denoising. In: 22nd Iberoamerican Congress on Pattern Recognition, At Santiago, Chile (Nov. 2017)
Gonzalez, R.C., Woods, R.: Digital Image Processing, 3rd edn. Prentice Hall, Upper Sadle River (2008)
Sharif, M., Hussain, A., Jaffar, M.A., et al.: Fuzzy-based hybrid filter for Rician noise removal. SIViP 10, 215 (2016). https://doi.org/10.1007/s11760-014-0729-1
Liu, L., Philip Chen, C.L., Zhou, Y., et al.: A new weighted mean filter with a two-phase detector for removing impulse noise. Inf. Sci 315, 1–16 (2015). https://doi.org/10.1016/j.ins.2015.03.067
Lucy, L.B.: An iterative technique for the rectification of observed distribution. Astron. J. 79, 745 (1974)
Richardson, W.H.: Bayesian-based iterative method of image restoration. J. Opt. Soc. Am. 62, 55–59 (1972)
Gonzalez, R.C., et al.: Digital Image Processing Using MATLAB, 2nd edn. Gatesmark Publishing, Knoxville (2009)
Mignotte, M.: A segmentation based regularization term for image deconvolution. IEEE Trans. Image Process. 15, 1973–1984 (2006)
Siadat, M., Aghazadeh, N., Öktem, O.: Reordering for improving global Arnoldi–Tikhonov method in image restoration problems. SIViP 12, 497 (2018). https://doi.org/10.1007/s11760-017-1185-5
Adam, T., Paramesran, R.: Hybrid non-convex second-order total variation with applications to non-blind image deblurring. SIViP (2019). https://doi.org/10.1007/s11760-019-01531-3
Paik, J., Katsaggelos, A.: Image restoration using a modified hopfield network. IEEE Trans Image Process. 1(1), 49–63 (1992)
Bilal, M., et al.: Estimation and optimization based ill-posed inverse restoration using fuzzy logic. Multimed Tools Appl. 69(3), 1067–1087 (2014)
Huang, C., et al.: Robust image restoration via adaptive low-rank approximation and joint kernel regression. IEEE Trans. Image Process. 23, 5284–97 (2014)
Liu, J., et al.: An efficient variational method for image restoration. Abstr Appl Anal 213536, 1–11 (2013)
Le, J., et al.: A new efficient alternating method for image restoration and texture extraction. J. Comput. Inf. Syst. 9(7), 2595–2602 (2013)
Zhang, X., et al.: Non-blind deblurring of structured images with geometric deformation. Vis Comput. 3(2), 131–140 (2015)
Huang, H., Wang, K.: Texture-preserving deconvolution via image decomposition. SIViP 11, 1189 (2017). https://doi.org/10.1007/s11760-017-1074-y
Ren, W. et al.: Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation, 32 Neural Information Processing Systems (NIPS 2018), Montreal, Canada, pp. 297–307 (2018)
Bilal, M., Rehman, MSu, Jaffar, M.A.: Evolutionary reconstruction: image restoration for space variant degradation. Smart Comput. Rev 3(4), 220–232 (2013)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A Database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings 8th International Conference Computer Vision, vol. 2, pp. 416–423 (July 2001)
Roth, S., Black, M.J.: Fields of experts. Int. J. Comput. Vis. 82(2), 205–229 (2009)
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
Bilal, M., Arif, M. A generalized modeling of ill-posed inverse reconstruction of images using a novel data-driven framework. SIViP 14, 333–341 (2020). https://doi.org/10.1007/s11760-019-01559-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-019-01559-5