Our mission is to support companies and institutions for digitalizing, converting, and managing big collections of documents. State-of-the-art technologies help customers to take control of their data and are integrated in customized workflows.
Some of sugarcube's daily tasks are:
- The extraction of data from PDF files, images, and the most commonly used document formats.
- The application of artificial intelligence techniques for understanding the logical function of text (e.g. title, paragraphs, etc.)
- Data conversion into easily editable formats like XML, DOCX, etc.
- The production of replica ebooks.
- The development and the configuration of indexing systems able to deal with multimedia data and to calculate similarities among documents.
- The configuration of proprietary techniques of analysis for cleaning old paper images, detecting tables, identifying images, etc.
We help customers to automate the management of their documents, to recover information from printed books' images, to make information editable again, and so on.
Founded in 2010, the company is based in Fribourg (Switzerland) and mainly offers solutions on the European market. Among all our projects, we provided the first digital version of the Swiss Law, by cleaning, analysing and converting to XML more than half a million of scanned page in the three official languages.