Enhanced Bleed Through Removal Using Normalized Picture Information Based Measures

[摘要] Back-to-front interference is a common problem in documents, printed on translucent pages with insufficient opacity and is referred to as bleed through. The present state-of-art algorithms address bleed through based on entropy [1-3], entropic correlation [4] and discriminator analysis [5,10]. However, a common drawback of such algorithms is their inefficient processing of documents that are either sparse in terms of content or have a very dark background. Our proposed algorithm, based on Normalized Picture Information Measure (NPIM) [6] and Otsu's binarization method [5], addresses these problems. Experiments on 111 test images indicates that our algorithm performs comparable to state-of- the-art on 106 images and for the remaining 5 low contrast images our algorithm is able to remove bleed through whereas the state-of-the-art algorithms fail.

[发布机构] HP Development Company

[学科分类] 计算机科学（综合）

[关键词] bleed through;document cleanup