A restoration and binarization method for multi-spectral damaged document image

Abstract

Recently, researchers have started to focus on the use of multi-spectral system for document image analysis. This system provides different visions of the same document which brings to surface every hidden text. This paper suggests a new methodology dealing with document binarization and restoration problems. For document binarization, a couple of algorithms are performed to create two binary images. The first algorithm is based on a statistical feature and the second one, aims to fix the area of degradation in the document. These two binarization outputs are combined to generate a single binary mask. This mask is used in the second part of the methodology, which is the inpainting process to restore the initial look of the document image before degradation. The proposed methodology has been tested over two multi-spectral datasets. The obtained results show the effectiveness of the suggested method.