Full-Page text recognition

Recognising the full content of documents using OCR technologies

Full-Page text recognition

Hard copy records managed by enterprises are usually based on a general body text, which is then supplemented with unique details of specific transactions. There are much fewer physical records with unique data content. In order to display them in an electronic format and to search in them, these records need to be digitised. As a result, the information contained on them will be readable using OCR technology. Our system can convert such records into PDF format. Following conversion, the original record image can be displayed in a PDF reader. Information appearing on the pages can be selected and copied to the clipboard. In addition, users can also use all standard search functions. Hard copy records pre-processed this way can also be retrieved from the archive based on any part of the textual content.

Features

  • Digitise documents
  • Recognise the full content of scanned pages using OCR technology
  • Proof-correction, if necessary
  • Generate searchable PDF content
  • Archive physical records
  • Documents can be searched based on content, full-text search function
  • Electronic archive of certified documents
  • Direct control of scanners with different performance properties

Advantages

You can perform full-text searches in hard copy records because system capabilities are not limited to keyword-based searching.

When searching for an excerpt, you do not need to lose time going through the whole record page by page: you can use the standard search tools to find the required part in pre-processed documents any time.

General features

  • Bespoke solutions
  • Reliable systems tailored to the needs of financial institutions
  • Processes and data content can be designed by the principal
  • Solutions working closely with other systems used by the company