First Competition on Presentation Attack Detection on ID Card

TL;DR

This paper reports on the first competition evaluating presentation attack detection algorithms for ID cards, providing an independent assessment of current methods across diverse datasets from multiple countries.

Contribution

It introduces a new benchmark for ID card PAD algorithms with a sequestered, cross-dataset test set and evaluates state-of-the-art models in a competitive setting.

Findings

Top team achieved 77.65% average ranking

Eight models evaluated on four-country dataset

Provides baseline algorithms and evaluation protocol

Abstract

This paper summarises the Competition on Presentation Attack Detection on ID Cards (PAD-IDCard) held at the 2024 International Joint Conference on Biometrics (IJCB2024). The competition attracted a total of ten registered teams, both from academia and industry. In the end, the participating teams submitted five valid submissions, with eight models to be evaluated by the organisers. The competition presented an independent assessment of current state-of-the-art algorithms. Today, no independent evaluation on cross-dataset is available; therefore, this work determined the state-of-the-art on ID cards. To reach this goal, a sequestered test set and baseline algorithms were used to evaluate and compare all the proposals. The sequestered test dataset contains ID cards from four different countries. In summary, a team that chose to be "Anonymous" reached the best average ranking results of 74.80%, followed very closely by the "IDVC" team with 77.65%.