arXiv subjects

Christian Rathgeb

Publications and source records attributed to Christian Rathgeb.

At least 19 recordsLinked to original sources

arXiv2026

Vision Language Model Fusion for Explainable Face Recognition

Responsible deployment of face verification systems requires more than accurate decisions: systems should also provide interpretable and auditable evidence that enables users to understand, assess, and challenge their decisions. Vision-language models (VLMs) provide a promising foundation for explainable face recognition by combining visual analysis with natural-language reasoning. However, relying on a single model may further limit the decision accuracy as well as provided explanations. This work therefore investigates whether multiple VLMs can be combined to improve recognition accuracy, and to enrich the explanations associated with those decisions. This work evaluates four VLMs as standalone face verification systems and subsequently proposes a fusion framework, where two source models provide similarity scores and textual justifications and a third VLM acts as a decider model. Four different fusion scenarios are considered, progressively providing the decider model with scores, justifications, face images, and combinations of these modalities. Overall, the findings suggest that the value of multi-VLM fusion extends beyond recognition performance. VLMs can provide complementary justifications and perspectives that enable richer explanations of face recognition decisions, supporting greater transparency, auditability, and error analysis. This is relevant to the development of responsible explainable face verification systems, where users and operators should be able to understand not only the final decision but also the evidence and potential sources underlying it. The proposed multimodal VLM, which combines decision scores, explanations, and face images, achieves higher recognition accuracy than state-of-the-art VLMs and domain-specific face recognition models, while also providing fused explanations that are expected to be more robust than those generated by individual VLMs.

cs.CV↗

arXiv2026

Image Quality Assessment of Identity Cards Using Measures from Open Face Image Quality

This paper addresses the challenge of assessing image quality in ID cards in remote verification systems by applying capture-related quality measures from the Open Face Image Quality (OFIQ) standard to ID card images. Our preprocessing pipeline includes corner detection, perspective normalization, and comprehensive foreground masking to ensure accurate and unbiased quality measure computation. We evaluate the effectiveness of these measures by analyzing their correlation with the performance of three presentation attack detection (PAD) algorithms across four diverse ID card datasets, where two datasets contain bona fide, i.e. pristine, images and two contain printed mock ID cards. Our results suggest that quality assessment based on some OFIQ measures can significantly improve PAD performance.

cs.CV↗

arXiv2026

Detection of T-shirt Presentation Attacks in Face Recognition Systems

Face recognition systems are often used for biometric authentication. Nevertheless, it is known that without any protective measures, face recognition systems are vulnerable to presentation attacks. To tackle this security problem, methods for detecting presentation attacks have been developed and shown good detection performance on several benchmark datasets. However, generalising presentation attack detection methods to new and novel types of attacks is an ongoing challenge. In this work, we employ 1,608 T-shirt attacks of the T-shirt Face Presentation Attack (TFPA) database using 100 unique presentation attack instruments together with 152 bona fide presentations. In a comprehensive evaluation, we show that this type of attack can compromise the security of face recognition systems. Furthermore, we propose a detection method based on spatial consistency checks in order to detect said T-shirt attacks. Precisely, state-of-the-art face and person detectors are combined to analyse the spatial positions of detected faces and persons based on which T-shirt attacks can be reliably detected.

cs.CV↗

arXiv2026

DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection

In this work, we introduce DifFoundMAD, a parameter-efficient D-MAD framework that exploits the generalisation capabilities of vision foundation models (FM) to capture discrepancies between suspected morphs and live capture images. In contrast to conventional D-MAD systems that rely on face recognition embeddings or handcrafted feature differences, DifFoundMAD follows the standard differential paradigm while replacing the underlying representation space with embeddings extracted from FMs. By combining lightweight finetuning with class-balanced optimisation, the proposed method updates only a small subset of parameters while preserving the rich representational priors of the underlying FMs. Extensive cross-database evaluations on standard D-MAD benchmarks demonstrate that DifFoundMAD achieves consistent improvements over state-of-the-art systems, particularly at the strict security levels required in operational deployments such as border control: The error rates reported in the current state-of-the-art were reduced from 6.16% to 2.17% for high-security levels using DifFoundMAD

cs.CV↗

arXiv2025

Training-free Dimensionality Reduction via Feature Truncation: Enhancing Efficiency in Privacy-preserving Multi-Biometric Systems

Biometric recognition is widely used, making the privacy and security of extracted templates a critical concern. Biometric Template Protection schemes, especially those utilizing Homomorphic Encryption, introduce significant computational challenges due to increased workload. Recent advances in deep neural networks have enabled state-of-the-art feature extraction for face, fingerprint, and iris modalities. The ubiquity and affordability of biometric sensors further facilitate multi-modal fusion, which can enhance security by combining features from different modalities. This work investigates the biometric performance of reduced multi-biometric template sizes. Experiments are conducted on an in-house virtual multi-biometric database, derived from DNN-extracted features for face, fingerprint, and iris, using the FRGC, MCYT, and CASIA databases. The evaluated approaches are (i) explainable and straightforward to implement under encryption, (ii) training-free, and (iii) capable of generalization. Dimensionality reduction of feature vectors leads to fewer operations in the Homomorphic Encryption (HE) domain, enabling more efficient encrypted processing while maintaining biometric accuracy and security at a level equivalent to or exceeding single-biometric recognition. Our results demonstrate that, by fusing feature vectors from multiple modalities, template size can be reduced by 67 % with no loss in Equal Error Rate (EER) compared to the best-performing single modality.

cs.CV↗

arXiv2025

Closing the Performance Gap in Biometric Cryptosystems: A Deeper Analysis on Unlinkable Fuzzy Vaults

This paper analyses and addresses the performance gap in the fuzzy vault-based \ac{BCS}. We identify unstable error correction capabilities, which are caused by variable feature set sizes and their influence on similarity thresholds, as a key source of performance degradation. This issue is further compounded by information loss introduced through feature type transformations. To address both problems, we propose a novel feature quantization method based on \it{equal frequent intervals}. This method guarantees fixed feature set sizes and supports training-free adaptation to any number of intervals. The proposed approach significantly reduces the performance gap introduced by template protection. Additionally, it integrates seamlessly with existing systems to minimize the negative effects of feature transformation. Experiments on state-of-the-art face, fingerprint, and iris recognition systems confirm that only minimal performance degradation remains, demonstrating the effectiveness of the method across major biometric modalities.

cs.CV↗

arXiv2025

AMB-FHE: Adaptive Multi-biometric Fusion with Fully Homomorphic Encryption

Biometric systems strive to balance security and usability. The use of multi-biometric systems combining multiple biometric modalities is usually recommended for high-security applications. However, the presentation of multiple biometric modalities can impair the user-friendliness of the overall system and might not be necessary in all cases. In this work, we present a simple but flexible approach to increase the privacy protection of homomorphically encrypted multi-biometric reference templates while enabling adaptation to security requirements at run-time: An adaptive multi-biometric fusion with fully homomorphic encryption (AMB-FHE). AMB-FHE is benchmarked against a bimodal biometric database consisting of the CASIA iris and MCYT fingerprint datasets using deep neural networks for feature extraction. Our contribution is easy to implement and increases the flexibility of biometric authentication while offering increased privacy protection through joint encryption of templates from multiple modalities.

cs.CR↗

arXiv2025

Deep Learning-based Compression Detection for explainable Face Image Quality Assessment

The assessment of face image quality is crucial to ensure reliable face recognition. In order to provide data subjects and operators with explainable and actionable feedback regarding captured face images, relevant quality components have to be measured. Quality components that are known to negatively impact the utility of face images include JPEG and JPEG 2000 compression artefacts, among others. Compression can result in a loss of important image details which may impair the recognition performance. In this work, deep neural networks are trained to detect the compression artefacts in a face images. For this purpose, artefact-free facial images are compressed with the JPEG and JPEG 2000 compression algorithms. Subsequently, the PSNR and SSIM metrics are employed to obtain training labels based on which neural networks are trained using a single network to detect JPEG and JPEG 2000 artefacts, respectively. The evaluation of the proposed method shows promising results: in terms of detection accuracy, error rates of 2-3% are obtained for utilizing PSNR labels during training. In addition, we show that error rates of different open-source and commercial face recognition systems can be significantly reduced by discarding face images exhibiting severe compression artefacts. To minimize resource consumption, EfficientNetV2 serves as basis for the presented algorithm, which is available as part of the OFIQ software.

cs.CV↗

arXiv2024

TetraLoss: Improving the Robustness of Face Recognition against Morphing Attacks

Face recognition systems are widely deployed in high-security applications such as for biometric verification at border controls. Despite their high accuracy on pristine data, it is well-known that digital manipulations, such as face morphing, pose a security threat to face recognition systems. Malicious actors can exploit the facilities offered by the identity document issuance process to obtain identity documents containing morphed images. Thus, subjects who contributed to the creation of the morphed image can with high probability use the identity document to bypass automated face recognition systems. In recent years, no-reference (i.e., single image) and differential morphing attack detectors have been proposed to tackle this risk. These systems are typically evaluated in isolation from the face recognition system that they have to operate jointly with and do not consider the face recognition process. Contrary to most existing works, we present a novel method for adapting deep learning-based face recognition systems to be more robust against face morphing attacks. To this end, we introduce TetraLoss, a novel loss function that learns to separate morphed face images from its contributing subjects in the embedding space while still achieving high biometric verification performance. In a comprehensive evaluation, we show that the proposed method can significantly enhance the original system while also significantly outperforming other tested baseline methods.

cs.CV↗

arXiv2024

Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data

Synthetic data is gaining increasing popularity for face recognition technologies, mainly due to the privacy concerns and challenges associated with obtaining real data, including diverse scenarios, quality, and demographic groups, among others. It also offers some advantages over real data, such as the large amount of data that can be generated or the ability to customize it to adapt to specific problem-solving needs. To effectively use such data, face recognition models should also be specifically designed to exploit synthetic data to its fullest potential. In order to promote the proposal of novel Generative AI methods and synthetic data, and investigate the application of synthetic data to better train face recognition systems, we introduce the 2nd FRCSyn-onGoing challenge, based on the 2nd Face Recognition Challenge in the Era of Synthetic Data (FRCSyn), originally launched at CVPR 2024. This is an ongoing challenge that provides researchers with an accessible platform to benchmark i) the proposal of novel Generative AI methods and synthetic data, and ii) novel face recognition systems that are specifically proposed to take advantage of synthetic data. We focus on exploring the use of synthetic data both individually and in combination with real data to solve current challenges in face recognition such as demographic bias, domain adaptation, and performance constraints in demanding situations, such as age disparities between training and testing, changes in the pose, or occlusions. Very interesting findings are obtained in this second edition, including a direct comparison with the first one, in which synthetic databases were restricted to DCFace and GANDiffFace.

cs.CV↗

arXiv2024

Fairness measures for biometric quality assessment

Quality assessment algorithms measure the quality of a captured biometric sample. Since the sample quality strongly affects the recognition performance of a biometric system, it is essential to only process samples of sufficient quality and discard samples of low-quality. Even though quality assessment algorithms are not intended to yield very different quality scores across demographic groups, quality score discrepancies are possible, resulting in different discard ratios. To ensure that quality assessment algorithms do not take demographic characteristics into account when assessing sample quality and consequently to ensure that the quality algorithms perform equally for all individuals, it is crucial to develop a fairness measure. In this work we propose and compare multiple fairness measures for evaluating quality components across demographic groups. Proposed measures, could be used as potential candidates for an upcoming standard in this important field.

cs.CV↗

arXiv2024

Testing the Performance of Face Recognition for People with Down Syndrome

The fairness of biometric systems, in particular facial recognition, is often analysed for larger demographic groups, e.g. female vs. male or black vs. white. In contrast to this, minority groups are commonly ignored. This paper investigates the performance of facial recognition algorithms on individuals with Down syndrome, a common chromosomal abnormality that affects approximately one in 1,000 births per year. To do so, a database of 98 individuals with Down syndrome, each represented by at least five facial images, is semi-automatically collected from YouTube. Subsequently, two facial image quality assessment algorithms and five recognition algorithms are evaluated on the newly collected database and on the public facial image databases CelebA and FRGCv2. The results show that the quality scores of facial images for individuals with Down syndrome are comparable to those of individuals without Down syndrome captured under similar conditions. Furthermore, it is observed that face recognition performance decreases significantly for individuals with Down syndrome, which is largely attributed to the increased likelihood of false matches.

cs.CV↗

arXiv2024

TattTRN: Template Reconstruction Network for Tattoo Retrieval

Tattoos have been used effectively as soft biometrics to assist law enforcement in the identification of offenders and victims, as they contain discriminative information, and are a useful indicator to locate members of a criminal gang or organisation. Due to various privacy issues in the acquisition of images containing tattoos, only a limited number of databases exists. This lack of databases has delayed the development of new methods to effectively retrieve a potential suspect's tattoo images from a candidate gallery. To mitigate this issue, in our work, we use an unsupervised generative approach to create a balanced database consisting of 28,550 semi-synthetic images with tattooed subjects from 571 tattoo categories. Further, we introduce a novel Tattoo Template Reconstruction Network (TattTRN), which learns to map the input tattoo sample to its respective tattoo template to enhance the distinguishing attributes of the final feature embedding. Experimental results with real data, i.e., WebTattoo and BIVTatt databases, demonstrate the soundness of the presented approach: an accuracy of up to 99% is achieved for checking at most the first 20 entries of the candidate list.

cs.CV↗

arXiv2024

Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data

Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new sub-tasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

cs.CV↗

arXiv2024

Synthetic Data for the Mitigation of Demographic Biases in Face Recognition

This study investigates the possibility of mitigating the demographic biases that affect face recognition technologies through the use of synthetic data. Demographic biases have the potential to impact individuals from specific demographic groups, and can be identified by observing disparate performance of face recognition systems across demographic groups. They primarily arise from the unequal representations of demographic groups in the training data. In recent times, synthetic data have emerged as a solution to some problems that affect face recognition systems. In particular, during the generation process it is possible to specify the desired demographic and facial attributes of images, in order to control the demographic distribution of the synthesized dataset, and fairly represent the different demographic groups. We propose to fine-tune with synthetic data existing face recognition systems that present some demographic biases. We use synthetic datasets generated with GANDiffFace, a novel framework able to synthesize datasets for face recognition with controllable demographic distribution and realistic intra-class variations. We consider multiple datasets representing different demographic groups for training and evaluation. Also, we fine-tune different face recognition systems, and evaluate their demographic fairness with different metrics. Our results support the proposed approach and the use of synthetic data to mitigate demographic biases in face recognition.

cs.CV↗

arXiv2024

Double Trouble? Impact and Detection of Duplicates in Face Image Datasets

Various face image datasets intended for facial biometrics research were created via web-scraping, i.e. the collection of images publicly available on the internet. This work presents an approach to detect both exactly and nearly identical face image duplicates, using file and image hashes. The approach is extended through the use of face image preprocessing. Additional steps based on face recognition and face image quality assessment models reduce false positives, and facilitate the deduplication of the face images both for intra- and inter-subject duplicate sets. The presented approach is applied to five datasets, namely LFW, TinyFace, Adience, CASIA-WebFace, and C-MS-Celeb (a cleaned MS-Celeb-1M variant). Duplicates are detected within every dataset, with hundreds to hundreds of thousands of duplicates for all except LFW. Face recognition and quality assessment experiments indicate a minor impact on the results through the duplicate removal. The final deduplication data is publicly available.

cs.CV↗

arXiv2023

MCLFIQ: Mobile Contactless Fingerprint Image Quality

We propose MCLFIQ: Mobile Contactless Fingerprint Image Quality, the first quality assessment algorithm for mobile contactless fingerprint samples. To this end, we re-trained the NIST Fingerprint Image Quality (NFIQ) 2 method, which was originally designed for contact-based fingerprints, with a synthetic contactless fingerprint database. We evaluate the predictive performance of the resulting MCLFIQ model in terms of Error-vs.-Discard Characteristic (EDC) curves on three real-world contactless fingerprint databases using three recognition algorithms. In experiments, the MCLFIQ method is compared against the original NFIQ 2.2 method, a sharpness-based quality assessment algorithm developed for contactless fingerprint images \rev{and the general purpose image quality assessment method BRISQUE. Furthermore, benchmarks on four contact-based fingerprint datasets are also conducted.} Obtained results show that the fine-tuning of NFIQ 2 on synthetic contactless fingerprints is a viable alternative to training on real databases. Moreover, the evaluation shows that our MCLFIQ method works more accurate and robust compared to all baseline methods on contactless fingerprints. We suggest considering the proposed MCLFIQ method as a \rev{starting point for the development of} a new standard algorithm for contactless fingerprint quality assessment.

cs.CV↗

arXiv2023

Pose Impact Estimation on Face Recognition using 3D-Aware Synthetic Data with Application to Quality Assessment

Evaluating the quality of facial images is essential for operating face recognition systems with sufficient accuracy. The recent advances in face quality standardisation (ISO/IEC CD3 29794-5) recommend the usage of component quality measures for breaking down face quality into its individual factors, hence providing valuable feedback for operators to re-capture low-quality images. In light of recent advances in 3D-aware generative adversarial networks, we propose a novel dataset, Syn-YawPitch, comprising 1000 identities with varying yaw-pitch angle combinations. Utilizing this dataset, we demonstrate that pitch angles beyond 30 degrees have a significant impact on the biometric performance of current face recognition systems. Furthermore, we propose a lightweight and explainable pose quality predictor that adheres to the draft international standard of ISO/IEC CD3 29794-5 and benchmark it against state-of-the-art face image quality assessment algorithms

cs.CV↗