Automated Document Classification

OnBase captures documents, whether scanned images or electronic-born documents, into a central digital repository for processing.

Once documents have been captured, OnBase can automatically identify them as well. With automated document classification, staff no longer need to manually sort and route documents - OnBase does the thinking for you. 

OnBase automated document classification identifies documents in several ways, including:

  • Barcode recognition - The software simply reads a barcode on a document to identify the type of document.
  • Image identification – OnBase can use an image, like a logo, to identify a document. This identification is dependent on the quality of the image on the document
  • Single word/phrase identification – If a single word or phrase, i.e. the document title, is always in the same location on the page, OnBase can use it to identify the document

Making the complex simple with document classification software

For more complex documents, the OnBase intelligent classification solution can search the entire document, looking for specific attributes of the information on the page – including how information is organised on the page, what type of information is present and even contextual clues within the content. 

Over time, the solution learns from classification successes and errors to process similar documents faster and more accurately. And, when added to an OnBase content management solution, the automated document classification solution can use documents already stored in the OnBase repository to learn attributes of specific document types before ever capturing new documents. 

Once classified, these documents can be sent further into the capture process for data extraction, routed directly into your content management system or network directory or stored within OnBase for further processing. 


aiim whitepaper