Document Segmentation with Application forthe Book Publishing Industry

摘要

We describe a method of segmenting a scanned page into Text,Image, Line-Art and background. Each segment undergoes specific imageprocessing and compression routines, based on its type, and the document isthen reassembled as in the original page. This procedure improves the printquality of the document, being as close as possible to the paper original, andeliminates artifacts that would otherwise result in printing a scanned document.Moreover, the disparate compression algorithms yield a reduced size file,improving performance in printers, servers, and networks.