A nonlinear blind source separation solution for removing the show-through effect in the scanned documents

Digital documents are usually degraded during the scanning process due to the printings existing on the backside of the scanning manuscript. This is often caused by the so called show-through effect, the image that interferes with the main picture due to the intrinsic opacity of the paper. This phenomenon is on type of degradation that one would like to remove. In this paper, we propose a novel and general nonlinear model for show-through phenomenon. A nonlinear blind source separation (BSS) algorithm is used for this particular application in a new recursive and extendible structure for compensating show-through. Finally, we introduce a new structure for removing the show-through and the blurring effect which appears during the scanning process simultaneously.

[1]  Yujie Zhang,et al.  Linear and nonlinear ICA based on mutual information , 2007, 2007 International Symposium on Intelligent Signal Processing and Communication Systems.

[2]  Ali Mansour,et al.  Blind Separation of Sources , 1999 .

[3]  Christian Jutten,et al.  Source separation in post-nonlinear mixtures , 1999, IEEE Trans. Signal Process..

[4]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[5]  Hirobumi Nishida,et al.  A multiscale approach to restoring scanned color document images with show-through effects , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

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

[7]  Massoud Babaiezadeh Malmiri.  On blind source separation in convolutive and nonlinear mixtures , 2002 .

[8]  Chew Lim Tan,et al.  Matching of double-sided document images to remove interference , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  C. Jutten,et al.  On the separability of nonlinear mixtures of temporally correlated sources , 2003, IEEE Signal Processing Letters.

[10]  Yannick Deville,et al.  Blind Maximum Likelihood Separation of a Linear-Quadratic Mixture , 2004, ICA.

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

[12]  Anna Tonazzini,et al.  Fast correction of bleed-through distortion in grayscale documents by a blind source separation technique , 2007, International Journal of Document Analysis and Recognition (IJDAR).

[13]  Chew Lim Tan,et al.  Document image enhancement using directional wavelet , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[15]  Christian Jutten,et al.  Three easy ways for separating nonlinear mixtures? , 2004, Signal Process..