Joint enhancement-compression of handwritten document images through DjVu encoder

摘要

Despite all the technological developments in image acquisition and processing, preserving old documents and other data of historical interest is still a very challenging issue. Indeed, these documents are often proned to several types of artifacts affecting their readability. Furthermore, due to the considerable information considered in such media, reducing the size of the digitized documents is another challenging problem since their entropy is often high due to the presence of artifacts. Thus, we believe that directing the lost of information onto artifacts could bring an elegant solution to this issue. In this paper, we propose the first approach joining enhancement-compression for handwritten document images. This approach presents a novel foreground/background segmentation algorithm, using both directional and contrast features to highlight the original information. This pre-treatment step is embedded into DjVu encoder, which is commonly used in National Archives and libraries frameworks, to drive the compression rate. Both objective evaluation and perceptual judgment demonstrate the efficiency of the proposed scheme on the whole DIBCO datasets. (C) 2016 Elsevier Inc. All rights reserved.