Paul Andreas successfully defended his Master thesis on
„Assessing Lossy Image Compression for Face Recognition“
as part of the TeleTrusT EAB workshop presentations (25.03.2026).
Biometric face verification requires that a biometric probe can be compared against a reference sample, which in the case of ICAO compliant MRTDs is stored as a JPEG or JPEG 2000 image. In order to avoid equipping temporary ID documents with expensive RFID chips for machine readability, the reference sample should be encoded in conventional 2D barcodes. This saves resources and speeds up the issuing process, but comes with the challenge of storing the face images at significantly smaller storage capacities. For this reason, it is important to reduce the file size of these images to a maximum of 1024 bytes.
This study examines preprocessing steps and compression configurations that can be used to achieve this target size while minimizing the impact on the performance of face recognition algorithms. Therefore seven compression algorithms are examined, namely JPEG, JPEG 2000, JPEG XL, JPEG AI, HEIF, AVIF, and WebP. While the reference sample must always comply with ICAO specifications, the individual samples may or may not meet these requirements, depending on the application. This work identifies the optimal compression steps for both of these scenarios.
It is shown that in both scenarios, JPEG AI, when using optimized settings, provides the best face recognition performance, closely followed by AVIF and WebP. The losses caused by the strong lossy compression are comparatively small. For the comparison of ICAO-compliant face images only, converting the images to grayscale proves to be an important preprocessing step, whereas for comparisons involving less suitable samples, preserving color is essential. In addition, smoothing and resizing the images beforehand also turns out to be beneficial.