Parameter Estimation in TV Image Restoration Using Variational Distribution Approximation

In this paper, we propose novel algorithms for total variation (TV) based image restoration and parameter estimation utilizing variational distribution approximations. Within the hierarchical Bayesian formulation, the reconstructed image and the unknown hyperparameters for the image prior and the noise are simultaneously estimated. The proposed algorithms provide approximations to the posterior distributions of the latent variables using variational methods. We show that some of the current approaches to TV-based image restoration are special cases of our framework. Experimental results show that the proposed approaches provide competitive performance without any assumptions about unknown hyperparameters and clearly outperform existing methods when additional information is included.

[1]  David J. C. MacKay,et al.  Ensemble Learning for Blind Image Separation and Deconvolution , 2000 .

[2]  V. Šmídl,et al.  The Variational Bayes Method in Signal Processing , 2005 .

[3]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.

[4]  Bernard Rougé,et al.  TV Based Image Restoration with Local Constraints , 2003, J. Sci. Comput..

[5]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[6]  Arun N. Netravali,et al.  Image Restoration Based on a Subjective Criterion , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[8]  Aggelos K. Katsaggelos,et al.  Blind Deconvolution Using a Variational Approach to Parameter, Image, and Blur Estimation , 2006, IEEE Transactions on Image Processing.

[9]  Raymond H. Chan,et al.  Cosine transform based preconditioners for total variation deblurring , 1999, IEEE Trans. Image Process..

[10]  Edmund Y. Lam,et al.  A Total Variation Regularization Based Super-Resolution Reconstruction Algorithm for Digital Video , 2007, EURASIP J. Adv. Signal Process..

[11]  Rafael Molina,et al.  On the Hierarchical Bayesian Approach to Image Restoration: Applications to Astronomical Images , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Matthew J. Beal.  Variational algorithms for approximate Bayesian inference , 2003 .

[13]  Nando de Freitas,et al.  An Introduction to MCMC for Machine Learning , 2004, Machine Learning.

[14]  Harri Lappalainen,et al.  Ensemble learning for independent component analysis , 1999 .

[15]  Aggelos K. Katsaggelos,et al.  Total Variation Image Restoration and Parameter Estimation using Variational Posterior Distribution Approximation , 2007, 2007 IEEE International Conference on Image Processing.

[16]  Brian D. Ripley,et al.  Spatial Statistics: Ripley/Spatial Statistics , 2005 .

[17]  José M. Bioucas-Dias,et al.  Adaptive total variation image deconvolution: A majorization-minimization approach , 2006, 2006 14th European Signal Processing Conference.

[18]  M. Ng,et al.  Superresolution image reconstruction using fast inpainting algorithms , 2007 .

[19]  Yen-Wei Chen,et al.  Ensemble learning for independent component analysis , 2006, Pattern Recognit..

[20]  José M. Bioucas-Dias,et al.  Total Variation-Based Image Deconvolution: a Majorization-Minimization Approach , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[21]  Nikolas P. Galatsanos,et al.  Hierarchical Bayesian image restoration from partially known blurs , 2000, IEEE Trans. Image Process..

[22]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[23]  A. Nehorai,et al.  Deconvolution methods for 3-D fluorescence microscopy images , 2006, IEEE Signal Processing Magazine.

[24]  A.K. Katsaggelos,et al.  A general framework for frequency domain multi-channel signal processing , 1993, IEEE Trans. Image Process..

[25]  A. Ben Hamza,et al.  Unifying probabilistic and variational estimation , 2002, IEEE Signal Process. Mag..

[26]  Nikolas P. Galatsanos,et al.  Hierarchical Bayesian image restoration from partially-known blurs , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[27]  Curtis R. Vogel,et al.  Ieee Transactions on Image Processing Fast, Robust Total Variation{based Reconstruction of Noisy, Blurred Images , 2022 .

[28]  Nikolas P. Galatsanos,et al.  A variational approach for Bayesian blind image deconvolution , 2004, IEEE Transactions on Signal Processing.

[29]  Aggelos K. Katsaggelos,et al.  Bayesian and regularization methods for hyperparameter estimation in image restoration , 1999, IEEE Trans. Image Process..

[30]  Michael I. Jordan,et al.  Bayesian parameter estimation via variational methods , 2000, Stat. Comput..

[31]  Aggelos K. Katsaggelos,et al.  Spatially adaptive iterative algorithm for the restoration of astronomical images , 1995, Int. J. Imaging Syst. Technol..

[32]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[33]  R. Steele.  Optimization , 2005 .

[34]  Christopher M. Bishop,et al.  Variational Relevance Vector Machines , 2000, UAI.

[35]  Andy M. Yip,et al.  Recent Developments in Total Variation Image Restoration , 2004 .

[36]  Aggelos K. Katsaggelos,et al.  A Bayesian approach for the estimation and transmission of regularization parameters for reducing blocking artifacts , 2000, IEEE Trans. Image Process..

[37]  Christopher M. Bishop,et al.  Bayesian Hierarchical Mixtures of Experts , 2002, UAI.

[38]  Tony F. Chan,et al.  Image processing and analysis - variational, PDE, wavelet, and stochastic methods , 2005 .

[39]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[40]  Nikolas P. Galatsanos,et al.  Hyperparameter estimation in image restoration problems with partially known blurs , 2002 .