Capturing data from various types of documents


Document scanning is typically followed by digitisation of content, i.e. capturing data from the documents. With this method, companies can significantly increase the speed of processing business documents and enhance employee efficiency. At Mikrografija, the scanned images are processed with the capturing, i.e. OCR tool, thus enabling the client to conduct full-text searches.

***

Why should data scanning and capture be entrusted to specialists? Because they will do a superb and flawless job of it. What is more, we are one of the few companies that can handle even the most challenging tasks. This is attested by the fact that, over the course of six months, we have managed to capture data from over several millions of documents.

With a high-quality OCR tool, we can capture data from the following types of documents:

  • structured documents (forms, issued invoices, payroll etc.),
  • semi-structured documents (received invoices, purchase orders, delivery notes etc.),
  • unstructured documents (letters, contracts, fax messages, SMS/MMSs, e-mails etc.).

The result of optical character recognition is the possibility of using either full or partial texts from the document, which speeds up the search and also reduces/eliminates the need for manual classification of documents according to content. Data capturing can lower the costs of entering the data into the information system, reduce the time necessary to process documents, speed up data entry and minimise the chance of errors. Documents are processed at one common point, where any errors, e.g. missing data, can be discovered at the very beginning of the process.

What is more, our technical solutions support mass recognition of unique elements/characters (i.e. identifiers) from one particular document, e.g. bar codes.