Bundesamt für Sicherheit in der Informationstechnik

Optical Character Recognition in Identity Documents Inspection

Hinweis: Die internationalen Standards/Spezifikationen für Reisepässe werden von der ICAO (UN-Ebene) bzw. auf EU-Ebene festgelegt und sind in englischer Sprache formuliert. Beiträge des BSI, die in diesem Bereich Berücksichtigung finden sollen, müssen daher ebenfalls auf Englisch formuliert sein (vgl. hierzu auch die entsprechenden englischsprachigen Technischen Richtlinien auf der BSI-Website TR-03110, TR-03121, TR-03129, TR-03135, etc.). Deswegen finden Sie den folgenden Ausschreibungstext nur auf Englisch vor.


Each modern Machine Readable Travel Document (MRTD) like a passport or an ID card contains a standardized Machine Readable Zone (MRZ) with biographic data and an electronic chip. To access the chip, an access key is derived from the MRZ of a given MRTD. Subsequent checks consist of checking the printed biographic data against the chip’s content. Digitizing and checking the optical/visible part of a MRTD often takes a noticeable amount of time which can be a bottleneck in border control scenarios where travelers need to be checked rapidly.

Aim and Scope

Within the scope of a thesis, algorithmic approaches shall be evaluated to digitize and check the optical/visible part of a MRTD using just standard hardware e.g. a Raspberry Pi and a GNU/Linux-based operating system. The goal is to develop an open system that is able to digitize a passport or ID card, perform some basic checks on the images and in addition perform checks on the chip’s data.

The latest state of literature in the field of character recognition, image processing and analysis should be reviewed and evaluated. The following exemplary issues in the domain of image processing could be tailored and addressed in a thesis:

  • How could “consumer devices” like a Raspberry Pi be used to build robust MRTD checking devices?
  • How could OCR algorithms be used to build robust and fast bibliographic extractors for MRTDs?
  • Could variations and combination of algorithms result in faster and better processing performance?
  • How could machine learning techniques help to check MRTDs more reliable and fast?

Type of Thesis

Master- or Bachelor-thesis or Diploma (tailoring of scope), English language is preferred but German language is possible.

Field of Study

Students with computer science, business informatics, mathematics, physics or statistics background with an affinity for digital security or image processing.


Florian Rienhardt, Markus Münzel, Markus Nuppeney
Bundesamt für Sicherheit in der Informationstechnik
Referat D 13: Kontrollinfrastrukturen und -architekturen