Title :
Efficient conversion of digital documents to multilayer raster formats
Author :
Bottou, Léon ; Haffner, Patrick ; LeCun, Yann
Author_Institution :
AT&T Labs .-Res., USA
fDate :
6/23/1905 12:00:00 AM
Abstract :
How can we turn the description of a digital (i.e. electronically produced) document into something that is efficient for multi-layer raster formats? It is first shown that a foreground/background segmentation without overlapping foreground components can be more efficient for viewing or printing. Then, a new algorithm that prevents overlaps between foreground components while optimizing both the document quality and compression ratio is derived from the minimum description length (MDL) criterion. This algorithm makes the DjVu compression format significantly, more efficient on electronically produced documents. Comparisons with other formats are provided
Keywords :
data compression; data conversion; document image processing; image coding; image segmentation; printing; DjVu compression format; compression ratio; digital document conversion; document printing; document quality optimization; document viewing; electronically produced document description; foreground/background segmentation; minimum description length criterion; multi-layer raster formats; overlapping foreground components; Graphics; Image analysis; Image coding; Image color analysis; Image resolution; Image segmentation; Nonhomogeneous media; Page description languages; Printing; Rendering (computer graphics);
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953829
