3. April 2017
Optical character recognition and capturing at PEAX
Our OCR and capturing experts Nadine Clerc and Jeremias Märki explain the importance of OCR and capturing for PEAX.
What is OCR?
OCR is used to recognise and read optical characters. It is also known to automatically recognise text in images of scanned documents, making it readable by the computer and thus enabling a full text search in PDFs, for example. OCR is required for capturing.
What is capturing?
Document capturing is when documents are classified according to specific properties. PEAX uses capturing to recognise different document types, i.e. invoices, reminders, vouchers, end of year tax certificates, tax statements, insurance policies, receipts, etc. We also use it to read various information, such as invoice amounts and due dates.
How do you learn a system to capture?
To ensure precisely typed documents, the system is fed and trained with countless test documents. While manual corrections are still needed initially, the system quickly learns and gradually recognises the document type automatically.
How are OCR and capturing used at PEAX?
All documents sent to the PEAX portal via the scanning centre are prepared using OCR and classified using capturing. If a document is recognised as an 'invoice', it will immediately be filed under invoices.
How will OCR and capturing be further developed?
In future, OCR and capturing will also be used for documents sent to the PEAX portal via a PEAXbox email address or the upload function. In addition, we are currently in the process of training the system to automatically recognise more and more document types.
Why is capturing particularly important for PEAX Payment?
Thanks to capturing, all relevant payment details can be automatically read from invoices and entered into the document properties. The availability of such details enables invoices to be approved for payment in just a few clicks.
«Thanks to capturing, PEAX users will be able to pay invoices in PEAX in just two clicks!»