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

2026-02-11

AI Summary

This study addresses the inefficiency and subjectivity of manual verification of facial images in Machine Readable Travel Documents (MRTDs) against ICAO/ISO standards, as well as the significant biases in existing public datasets regarding non-compliant samples and demographic representation. To this end, we introduce DFIC, a large-scale dataset comprising approximately 58,000 images and 2,706 video clips that encompass diverse compliant and non-compliant conditions, with a subset exhibiting near-balanced demographic distribution for the first time. Leveraging this dataset, we propose an end-to-end automatic compliance verification method integrating a spatial attention mechanism, which outperforms state-of-the-art approaches on ICAO compliance assessment. The released dataset and model substantially enhance the fairness, generalization, and security of facial recognition systems.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Ethics, Bias, and Fairness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• ICAO compliance
• facial image dataset
• demographic imbalance
• MRTD
• automated verification

Innovation

• DFIC dataset
• ICAO compliance verification
• spatial attention mechanism
• balanced demographic distribution
• automated facial image validation