Home / Products / Application Library /

Optical Character Recognition

Complex Comprehensive online system for data mining from raster images or PDF documents

  • Automatic document recognition based on defined patterns
  • Data mining from scanned document
  • Mined and clean data storage in user friendly interface
  • Checking data format, sums and VAT rates
  • Checking completeness of data acquired
  • Validation compared to operation databases
  • Mined data export availability into other system (např. přes XML)
  • Mass import of scanned documents
  • Can define your own template documents


  • Mining selected data from PDF documents or raster images based on defined patterns
  • Cleaning and validating mined data – checking the accuracy of:
    • data format
    • VAT rates
    • data compared to the operation database (for example business relationships)
  • Adding certain data (for example business relationship address) from the operation database
  • Displays mined data in a user-friendly interface
  • Option of editing mined data and adding missing data
  • Mass import of scanned documents from disc (address book), e-mails (can be regularly downloaded) or other applications such as web services
  • Exporting mined and added data to XML format, etc.
  • Easy administration for:
    • documents already processed,
    • documents waiting to be processed and
    • documents determined for administrator revision
  • Business relationship records

Mining data from invoices

NET Genium OCR is often used to mine data from a large volume of printed invoices and then process them into the information system. The data mining application speeds up invoice processing because it feeds a large amount of information to the information system, so it does not need to be entered manually. Users who opt for automatic processing will have access to a pre-prepared set of documents. They open the document and click on the button for data mining. The application displays the mined data, users add the missing data and finalize the scanned document.

Every user will know how many invoices still need processing, how many invoices have already been processed and how many invoices needs administrator revision. The application can be also used on mobile devices.

  • Importing scanned documents
  • Starting data mining process
  • Finalizing documents
  • Evaluating finalized documents