Blind image separation for document restoration using plug-and-play approach

Xhenis Çoba, Fangchen FENG, Azeddine Beghdadi

Abstract: In this paper we propose a new method for document image restoration based on Blind Source Separation. The existing separation methods rely on the general properties of source images such as independence, sparsity, and non-negativity. In this work we show that by exploiting some characteristics of image denoising methods in a play-and-plug scheme, efficient BSS results could be achieved. In particular, we show that the use of BM3D and Non-local Means denoising methods as ingredients in the proposed scheme, which exploits the non-local properties of the image, leads to better image separation in terms of convergence rate and perceptual image quality. We also propose to use the dictionary-learning approach to take the concept of visual chirality into consideration. Finally, we apply the proposed scheme to document image restoration problem and show its advantage through experiments and objective performance evaluation.