Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{891688,
author = {Sojka, Petr and Hatlapatka, Radim},
address = {Manchester, UK},
booktitle = {Proceedings of DocEng 2010 conference},
doi = {http://dx.doi.org/10.1145/1860559.1860563},
keywords = {Authoring tools and systems; Categorization; Classification; Document presentation; Representations/Standards; Character recognition; Digital mathematical library; Digitisation workflow},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Manchester, UK},
isbn = {978-1-4503-0231-9},
pages = {3-12},
publisher = {ACM},
title = {Document Engineering for a Digital Library: PDF recompression using JBIG2 and other optimization of PDF documents},
url = {http://www.fi.muni.cz/usr/sojka/presentations/sojka-hatlapatka-doceng2010.pdf},
year = {2010}
}
TY - JOUR
ID - 891688
AU - Sojka, Petr - Hatlapatka, Radim
PY - 2010
TI - Document Engineering for a Digital Library: PDF recompression using JBIG2 and other optimization of PDF documents
PB - ACM
CY - Manchester, UK
SN - 9781450302319
KW - Authoring tools and systems
KW - Categorization
KW - Classification
KW - Document presentation
KW - Representations/Standards
KW - Character recognition
KW - Digital mathematical library
KW - Digitisation workflow
UR - http://www.fi.muni.cz/usr/sojka/presentations/sojka-hatlapatka-doceng2010.pdf
L2 - http://dx.doi.org/10.1145/1860559.1860563
N2 - Several innovative document transformations and tools developed in the process of building the Digital Mathematical Library DML-CZ http://dml.cz are described. The main result is our new PDF re-compression tool, developed using a enhanced jbig2enc library. Together with pdfsizeopt.py by Péter Szabó, we have managed to decrease PDF storage size and transmission needs by 62%: using both programs we reduced the size of the original already compressed PDFs to 38%. We briefly describe workflow and tools developed for creating the digital library. The batch digital signature stamper, the document similarity metrics which uses four different methods, a [meta]data validation process and math OCR tools represent some of the main [by]products. Such document engineering, together with Google Scholar indexing optimization, have led to the success of serving digitized and born-digital scientific math documents to the public in DML-CZ, and are being employed also in The European Digital Mathematics Library, EuDML.
ER -
SOJKA, Petr a Radim HATLAPATKA. Document Engineering for a Digital Library: PDF recompression using JBIG2 and other optimization of PDF documents. In \textit{Proceedings of DocEng 2010 conference}. Manchester, UK: ACM. s.~3-12. ISBN~978-1-4503-0231-9. doi:10.1145/1860559.1860563. 2010.
|
