Self-Ident Proof-of-Concept
The Self-Ident proof of concept investigates how reference image capture, guided portrait capture, local quality assessment and face comparison can be combined in a smartphone application. The aim is to gain practical experience with integrating on-device models and custom image analysis. Passport photo criteria serve as the domain guideline for suitable captures in the Self-Ident context. The application is designed as a research prototype.
The implemented flow covers reading the passport photo from a passport via NFC, as well as capturing a reference face from a photo of an identity document. A capture guide and feedback in the camera preview support the subsequent portrait capture. Shared quality rules evaluate the available measurements and generate concrete capture hints. The captured image is checked and, where the conditions allow, cropped automatically. In the review, the reference and captured images can be inspected and compared using selectable models, alignment methods and preprocessing steps. Raw metrics and result levels make the comparison decision transparent.
The result is a technical foundation for investigating local image analysis methods and how they interact within a traceable capture process. The report describes the implemented functions and assesses their technical prerequisites.
Downloads
| File | Description | File size |
|---|---|---|
Project Report (DE)
|
|
1 MB |