The digitization is primarily used for conservation and fast retrieving of information.
The digitizing process converts the scanned page to machine-readable text.

The file-name of each page contains meta-data like:

• issue number of the newspapers
• initials of the issue
• publication date
• page number

These information will be appendend to each article by the article separation.

Further detection criteria on the page:

• columns
• roof lines
• titles
• subtitles
• leaders
• texts
• picture legends
• photographers
• authors
• photos and graphics (drawings) must be differed
• spread sheets must be recognized
• advertisements must be recognized

These information is labeled and selected by the layout recognition and will be available for the article separation and PPS-Finder.