MCMC for joint noise reduction and missing data treatment in degraded video

Image sequence restoration has been steadily gaining importance with the increasing prevalence of visual digital media. Automated treatment of archived video material typically involves dealing with replacement noise in the form of "blotches" that have varying intensity levels and "grain" noise. In the case of replacement noise, the problem is essentially one of missing data that must be detected and then reconstructed based on surrounding spatio-temporal information, whereas the additive noise can be treated as a noise-reduction problem. It is typical to treat these problems as separate issues; however, it is clear that the presence of noise has an effect on the ability to detect missing data and vice versa. This paper therefore introduces a fully Bayesian specification for the problem that allows an algorithm to be designed that acknowledges and exploits the influences from each of the subprocesses, causing the observed degradation. Markov chain Monte Carlo (MCMC) methodology is applied to the joint detection and removal of both replacement and additive noise components. It can be seen that many of the previous processes presented for noise reduction and missing data treatment are special cases of the framework presented here.

[1]  Refractor.  Vision , 2000, The Lancet.

[2]  K OrJ.  Numerical Bayesian methods applied to signal processing , 1996 .

[3]  Anil Kokaram,et al.  System for the removal of impulsive noise in image sequences , 1992, Other Conferences.

[4]  Anil C. Kokaram,et al.  Joint interpolation, motion and parameter estimation for image sequences with missing data , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[5]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[6]  Anil C. Kokaram,et al.  Detection and removal of line scratches in degraded motion picture sequences , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[7]  William J. Fitzgerald,et al.  Detection and correction of speckle degradation in image sequences using a 3D Markov random field , 1993 .

[8]  Anil C. Kokaram,et al.  Motion picture restoration - digital algorithms for artefact suppression in degraded motion picture film and video , 2001 .

[9]  R. D. Morris,et al.  Stochastic and deterministic methods in motion picture restoration , 1994 .

[10]  Michael L. Lightstone,et al.  A new efficient approach for the removal of impulse noise from highly corrupted images , 1996, IEEE Trans. Image Process..

[11]  K. Riedel.  Numerical Bayesian Methods Applied to Signal Processing , 1996 .

[12]  Eric Dubois,et al.  Noise Reduction in Image Sequences Using Motion-Compensated Temporal Filtering , 1984, IEEE Trans. Commun..

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

[14]  Anil C. Kokaram,et al.  A System for Reconstruction of Missing Data in Image Sequences Using Sampled 3D AR Models and MRF Motion Priors , 1996, ECCV.

[15]  Anil C. Kokaram,et al.  Joint Detection, Interpolation, Motion and Parameter Estimation for Image Sequences with Missing Data , 1997, ICIAP.

[16]  G. Haan,et al.  Motion compensated noise filtering of image sequences , 1992 .

[17]  Reginald L. Lagendijk,et al.  Noise reduction for image sequences using an oriented pyramid thresholding technique , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[18]  Aggelos K Katsaggelos,et al.  A model-based pel-recursive motion estimation algorithm , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[19]  Gonzalo R. Arce,et al.  Multistage order statistic filters for image sequence processing , 1991, IEEE Trans. Signal Process..

[20]  Peter Strobach,et al.  Quadtree-Structured Linear Prediction Models for Image Sequence Processing , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Anil C. Kokaram,et al.  Detection of missing data in image sequences , 1995, IEEE Trans. Image Process..

[22]  M. Ibrahim Sezan,et al.  Motion-adaptive weighted averaging for temporal filtering of noisy image sequences , 1992, Electronic Imaging.

[23]  A. Murat Tekalp,et al.  Efficient multiframe Wiener restoration of blurred and noisy image sequences , 1992, IEEE Trans. Image Process..

[24]  Anil C. Kokaram,et al.  Noise reduction of image sequences as preprocessing for MPEG2 encoding , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[25]  Andrew L. Rukhin,et al.  Tools for statistical inference , 1991 .

[26]  Sanjit K. Mitra,et al.  Blotch and Scratch Detection in Image Sequences based on Rank Ordered Differences , 1997 .

[27]  Christoph Stiller.  Motion estimation for coding of moving video at 8 kbit/s with Gibbs-modeled vectorfield smoothing , 1990, Other Conferences.

[28]  Jun S. Liu,et al.  Covariance structure of the Gibbs sampler with applications to the comparisons of estimators and augmentation schemes , 1994 .

[29]  Eric Dubois,et al.  Bayesian Estimation of Motion Vector Fields , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  A. Tanju Erdem,et al.  Motion-compensated multiframe Wiener restoration of blurred and noisy image sequences , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[31]  William J. Fitzgerald,et al.  Replacement noise in image sequences-detection and interpolation by motion field segmentation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[32]  Richard Storey,et al.  Electronic detection and concealment of film dirt , 1985 .

[33]  Anil C. Kokaram,et al.  Interpolation of missing data in image sequences , 1995, IEEE Trans. Image Process..

[34]  Aggelos K. Katsaggelos,et al.  Spatio-Temporal Motion Compensated Noise Filtering Of Image Sequences , 1989, Other Conferences.