DFIC: Towards a balanced facial image dataset for automatic ICAO compliance verification

TL;DR

This paper introduces the DFIC dataset, a large, balanced collection of facial images and videos for developing automated ICAO compliance verification methods, demonstrating improved accuracy over existing approaches.

Contribution

The paper presents the DFIC dataset with diverse, balanced facial images and videos, and a novel spatial attention-based method for ICAO compliance verification, outperforming current state-of-the-art techniques.

Findings

DFIC dataset contains 58,000 images and 2706 videos of over 1000 subjects.

The proposed method outperforms existing ICAO compliance verification approaches.

DFIC dataset enhances robustness and fairness in facial recognition applications.

Abstract

Ensuring compliance with ISO/IEC and ICAO standards for facial images in machine-readable travel documents (MRTDs) is essential for reliable identity verification, but current manual inspection methods are inefficient in high-demand environments. This paper introduces the DFIC dataset, a novel comprehensive facial image dataset comprising around 58,000 annotated images and 2706 videos of more than 1000 subjects, that cover a broad range of non-compliant conditions, in addition to compliant portraits. Our dataset provides a more balanced demographic distribution than the existing public datasets, with one partition that is nearly uniformly distributed, facilitating the development of automated ICAO compliance verification methods. Using DFIC, we fine-tuned a novel method that heavily relies on spatial attention mechanisms for the automatic validation of ICAO compliance requirements, and we have compared it with the state-of-the-art aimed at ICAO compliance verification, demonstrating improved results. DFIC dataset is now made public (https://github.com/visteam-isr-uc/DFIC) for the training and validation of new models, offering an unprecedented diversity of faces, that will improve both robustness and adaptability to the intrinsically diverse combinations of faces and props that can be presented to the validation system. These results emphasize the potential of DFIC to enhance automated ICAO compliance methods but it can also be used in many other applications that aim to improve the security, privacy, and fairness of facial recognition systems.