Title :
Synthesis of images of historical documents for Web visualization
Author :
Mello, Carlos A B
Author_Institution :
Escola Politecnica de Pernambuco, UPE, Brazil
Abstract :
This paper describes a system for efficient storage and network transmission of images of historical documents. The images are segmented into two classes (paper and ink) with the use of an entropy-based segmentation algorithm. The information is then reassembled, synthetising an image visually close to the original document. The synthesis process works in both classes, using information acquired in the segmentation phase. All the information needed to rebuild the final synthetic image occupies, in average, 2 Kbytes performing a very efficient compression scheme.
Keywords :
Internet; data compression; data visualisation; document image processing; history; image coding; image segmentation; Web visualization; entropy-based segmentation; historical documents; image compression; image segmentation; image synthesis; network transmission; storage transmission; synthetic image; Data mining; Feature extraction; Image converters; Image segmentation; Image storage; Ink; Internet; Network synthesis; Optical character recognition software; Visualization;
Conference_Titel :
Multimedia Modelling Conference, 2004. Proceedings. 10th International
Print_ISBN :
0-7695-2084-7
DOI :
10.1109/MULMM.2004.1264989