Amongst all our web sites, we often ask our clients to introduce data from documents, like car data from the vehicle registration certificate or identity data from the ID card. At this time, this process remains manual, increasing both the time required and the risk of error. OCR are programs that read data from a picture or directly using the camera of a mobile device and turn information into usable text. This text can then be mapped with the different fields we want to extract and filled in automatically.

The goal of this internship is to find OCR programs that could be used in our websites and mobile applications to help reading data from documents. Multiple challenges should also be considered, like the possibility for the OCR to be available and working offline for our apps, or the use of the camera instead of having to upload a picture. A Proof of Concept (PoC) implementation will most likely be part of the internship to evaluate the program and show what can be achieved.​