Directed Assistance for Ink-Bleed Reduction in Old Documents

Abstract

Ink-bleed interference is a serious problem that affects the legibility of old documents. Ink-bleed can be reduced reasonably well using pixel classifation based on user supplied markup that labels examples of ink-bleed, foreground-ink, and background. The main challenge for this approach is ensuring that the user provides markup that suffiently captures the characteristics of the document. This is particularly troublesome for old documents that can exhibit significant change within the same page.

In this paper, we address this markup problem using a directed assistanceapproach. In our approach the user provides a small amount of initial markup. The image is then classified and low-confidence regions are grouped and displayed to the user for another round of markup. The idea is to direct the user to where markup is needed. In addition, local markup can be weighted in the classification algorithm to produce better results. While a simple idea, we show that this is an effective and useful way to reduce ink-bleed in old documents.