PAIRWISE MARKOV MODEL APPLIED TO UNSUPERVISED IMAGE SEPARATION

The paper deals with blind separation and recovery of a noisy mixture of two binary signals on two sensors. Such a model can be applied in the context of recovery of scanned documents subject to show-through and bleed-through effects. The problem can be considered as a blind source separation one. Due to a complex noise and data structure, it is tackled from the more general approach of Bayesian restoration. The data is assumed to follow a Pairwise Markov Chain model: it generalizes Hidden Markov Chain models but it still allows one to calculate the a posteriori distributions of the data. The Expectation-Maximization (EM) and Iterative Conditional Estimation (ICE) methods are considered for parameter estimation, yielding an unsupervised processing. Finally, simulations show the interest of our approach on simulated and real data.

[1]  Jean Pierre Delmas,et al.  An equivalence of the EM and ICE algorithm for exponential family , 1997, IEEE Trans. Signal Process..

[2]  Wojciech Pieczynski,et al.  Multisensor triplet Markov chains and theory of evidence , 2007, Int. J. Approx. Reason..

[3]  Christian Wolf,et al.  Document Ink Bleed-Through Removal with Two Hidden Markov Random Fields and a Single Observation Field , 2010, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Gaurav Sharma.  Cancellation of show-through in duplex scanning , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[5]  Neri Merhav,et al.  Hidden Markov processes , 2002, IEEE Trans. Inf. Theory.

[6]  Pierre Lanchantin,et al.  Unsupervised segmentation of randomly switching data hidden with non-Gaussian correlated noise , 2011, Signal Process..

[7]  T. Koski.  Hidden Markov Models for Bioinformatics , 2001 .

[8]  Pierre Lanchantin,et al.  UNSUPERVISED NON STATIONARY IMAGE SEGMENTATION USING TRIPLET MARKOV CHAINS , 2004 .

[9]  Pierre Comon,et al.  Handbook of Blind Source Separation: Independent Component Analysis and Applications , 2010 .

[10]  Anna Tonazzini,et al.  Bleed-Through Removal from Degraded Documents Using a Color Decorrelation Method , 2004, Document Analysis Systems.

[11]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[12]  Boaz Ophir,et al.  Show-Through Cancellation in Scanned Images using Blind Source Separation Techniques , 2007, 2007 IEEE International Conference on Image Processing.

[13]  Farnood Merrikh-Bayat,et al.  A nonlinear blind source separation solution for removing the show-through effect in the scanned documents , 2008, 2008 16th European Signal Processing Conference.

[14]  Pierre A. Devijver,et al.  Baum's forward-backward algorithm revisited , 1985, Pattern Recognit. Lett..

[15]  Stéphane Derrode,et al.  Signal and image segmentation using pairwise Markov chains , 2004, IEEE Transactions on Signal Processing.