Biometric Recognition: Interpretability, Explainability, and Interaction with Large-Scale Models

Dear Colleagues,

This Special Issue aims to explore the intersection of biometric recognition systems and the emerging paradigms of interpretability and explainability in artificial intelligence, particularly in the context of large-scale models (e.g., foundation models, large language models, and multimodal architectures). Biometric systems—such as those used for facial recognition, fingerprint analysis, and gait recognition—are being deployed increasingly frequently in critical and sensitive applications ranging from border control to personal device authentication. However, the opacity of the decision-making of these deep learning-based biometric systems raises significant concerns regarding trust, transparency, accountability, and ethical compliance.

With the advent of large-scale models and their growing capabilities in understanding and generating biometric, visual, and textual information, there is an urgent need to investigate how such models can be integrated into biometric systems while ensuring that their outputs are interpretable, fair, and verifiable. This Special Issue welcomes contributions that tackle these challenges through novel algorithms, system architectures, theoretical frameworks, evaluation methodologies, and real-world case studies. We encourage interdisciplinary perspectives, especially those combining biometrics with human-centered AI, explainable machine learning, and privacy-preserving techniques.

Topics of interest include, but are not limited to, the following:

• Interpretable deep learning models for biometric recognition.
• Explainable AI (XAI) methods for facial, iris, voice, and gait recognition.
• Role of large language models and multimodal foundation models in biometric analysis.
• Human–AI interactions in biometric systems: trust, feedback, and decision support.
• Visualization and interpretability tools for biometric features and decisions.
• Post hoc explanation techniques for biometric classifiers.
• Evaluating fairness, accountability, and bias in biometric AI systems.
• The integration of XAI methods into biometric pipelines for security and forensic applications.
• Zero-shot and few-shot biometric recognition using pretrained large-scale models.
• Privacy-aware biometric recognition with interpretable outcomes.

You may choose our Joint Special Issue in Sensors.

Prof. Dr. Hugo Proença
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Methods and Protocols is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• biometric recognition
• facial recognition
• fingerprint analysis
• gait recognition