An Effective Algorithm for Ink-Bleed through Removal in Document Images
Rajbir Kaur, Amandeep Kaur · 2011
When documents are written on both sides, quite often ink bleeds through the paper. This is a common phenomenon with old documents and low quality paper. With the presence of increased bleed-through, reading and deciphering the text becomes tedious. In this paper two methods are proposed for ink–bleed through removal. The first method is founded on Blind Segmentation Approach which exploits information from one side of the document and second method is based on the exploitation of information from both sides of the scanned document and founded on a registration process which aims at working on both the recto and verso sides simultaneously. These two methods are further compared with Otsu’s method which performs enhancement through thresholding.