公开(公告)号：AT451660T

公开(公告)日：2009-12-15

申请号：AT03751248

申请日：2003-10-12

Applicant: OLIVE SOFTWARE INC

Inventor： STERN YONATAN ,  STEINVIL EMIL

IPC: G06K9/34 ,  G06K9/00 ,  H04N1/21

Abstract: A system and a method for the conversion of archived documents to a digital format and storage of the data extracted in repositories which may be easily extracted and searched by a user over a network such as the Internet. The data is preferably stored in the form of microfilm, although optionally the present invention could be operative with other types of physical media, such as microfiche, paper and any type of printed material. The microfilm data is preferably divided and/or grouped into at least one file. Optionally and preferably, each file undergoes the following automatic processing stages: combining files; analyzing image layout; segmentation; OCR; optional segmentation improvement; and output to XML, or another suitable output data format and/or language. In the last stage, the data contained in the files is preferably extracted and then more preferably transmitted to the relevant repository unit.