Afid framework improves automated fingermark recognition and analysis accuracy
AFID: A Unified Open Framework for Automated Fingermark Identification, Quality Assessment and Feature Extraction
Computer Vision and Pattern Recognition
Summary
Identifying fingerprints from crime scenes is important, but many current computer tools are closed and use private data. The authors created AFID, an open and unified software system that can recognize fingerprints, judge their quality, and find features using the same underlying model. AFID works well even without complex image adjustments and matches or beats commercial tools on standard forensic tests. It also predicts which fingerprints are good enough to use and extracts key details accurately, all with one shared model.
What this means in practice
- •For forensic analysts: Use the AFID framework to improve fingerprint matching accuracy and speed using a single model for multiple tasks in forensic investigations.
- •For security system developers: Incorporate AFID’s open-source fingerprint processing pipeline to enhance biometric recognition quality and feature extraction in access control systems.
Authors
Tim Oblak, Rudolf Haraksim, Peter Peer
Abstract
Automated fingermark identification is the foundation of forensic investigation, yet progress in the field is held back by fragmented, closed-source solutions trained on private or discontinued data. We present AFID, a unified open-source framework for friction ridge image processing that performs recognition, quality assessment, and feature extraction based on a single shared encoder, trained exclusively on publicly available data. At its core is a fixed-length representation learned for identity discrimination, trained under heavy augmentation. Despite applying essentially no preprocessing beyond resizing and padding at inference, AFID sets a new state of the art in fixed-length fingermark recognition, leading identification across NIST SD 27 (67.6% rank-1) , SD 302 (54.9% rank-1), and SD 303 (67.6% rank-1), surpassing a commercial matcher on fingermarks. From the same frozen backbone, a quality assessment module predicts recognition utility more accurately than any compared baseline and generalizes across independent matchers, while lightweight decoders recover minutiae, ridge orientation, and segmentation competitive with dedicated methods. The framework proves that a single, efficiently trained encoder can support the full fingermark processing pipeline, from recognition through quality assessment all the way to feature extraction. To accelerate research on fingermark analysis even further, we release the code, models, and annotations to the community.