Search Results (122)

Background: The clinical value of the cerebroplacental ratio (CPR) for predicting adverse perinatal outcomes in unselected obstetric populations remains uncertain. We aimed to evaluate the prognostic performance of serial third-trimester fetal biometry and Doppler-derived CPR and to compare their ability to identify adverse perinatal outcomes and neonatal growth abnormalities. Methods: In this prospective longitudinal cohort study, 100 consecutive pregnancies from an unselected obstetric population underwent standardized ultrasonographic examinations at both 28 and 37 weeks of gestation. Fetal biometric measurements, estimated fetal weight (EFW), amniotic fluid index, umbilical and middle cerebral artery Doppler indices, and CPR were recorded. Maternal, obstetric, delivery, and neonatal data were collected prospectively. Receiver operating characteristic (ROC) curve analyses and parsimonious multivariable regression models, accompanied by 1000-sample bootstrap internal validation, were performed to evaluate the independent predictive capacity of fetal biometry and CPR metrics. Results: Gestational age-specific CPR percentiles were associated with expected physiological Doppler changes but showed limited associations with obstetric and neonatal outcomes. In separate parsimonious regression models optimized for event-per-variable ratios, neither 28-week nor 37-week CPR independently predicted composite adverse perinatal outcomes, NICU admission, low Apgar scores, or abnormal umbilical cord blood pH. Rigorous bootstrap internal validation confirmed that optimism-corrected area under the curve (AUC) values for CPR models remained close to chance (range: 0.463–0.507). In contrast, 37-week EFW independently predicted neonatal birth weight, while both 37-week EFW and EFW percentile demonstrated good discriminatory performance for identifying small-for-gestational-age neonates (AUC = 0.812 and 0.833, respectively; both p < 0.001). Maternal body mass index and late-pregnancy fetal biometry also showed moderate discriminatory performance for predicting large-for-gestational-age neonates. Overall, late-pregnancy biometry outperformed CPR for identifying growth abnormalities, whereas neither modality alone accurately predicted composite adverse perinatal outcomes. Conclusions: In an unselected obstetric population, serial third-trimester CPR provided limited additional prognostic information beyond routine fetal biometry. Late-pregnancy fetal biometry, particularly 37-week estimated fetal weight, demonstrated superior performance for identifying neonatal growth abnormalities. These findings support the continued use of conventional fetal biometry as the primary component of routine third-trimester surveillance, with CPR serving as a complementary rather than standalone Doppler parameter. Full article

Palm-vein recognition is an attractive biometric modality for secure access control because its subcutaneous vascular patterns are difficult to observe and reproduce externally. However, existing studies optimize the recognition algorithm and the hardware accelerator in isolation, and rarely satisfy the on-chip memory and energy constraints of edge devices. This paper presents a hardware-aware co-design of a lightweight FPGA accelerator for palm-vein recognition, in which the network is shaped by the cost structure of the target fabric and the inference engine is organized around the resulting layer shapes. On the algorithm side, a hardware-aware neural architecture search with deployment cost terms is combined with divisor-aligned structured pruning and INT8 quantization-aware training. Structured pruning reduces the model parameters to 0.32 M and the MACs to 87.2 M while preserving recognition accuracy. On the hardware side, a task-specific design space exploration selects a $14\times 12$ systolic array and an output-stationary dataflow that keeps all feature maps and weights on chip and reduces the modeled buffer-access count by 34.6% relative to the best alternative stationary dataflow. Implemented on a Xilinx Zynq-7100 at 100 MHz, the deployed INT8 checkpoint attains an accuracy of 99.50%, with a PL inference latency of 33.03 ms and an energy efficiency of 33.27 FPS/W. Full article

The security of a signature scheme given in the standard model (SM) will be more stable and reliable than that given in the random oracle model (ROM). Fuzzy identity-based signature (FIBS) enables a user to generate a signature for a set of descriptive attributes, defined as $\omega ={\left\{{\omega }_j\right\}}_{j=1}^n$. Any attributes set ${\omega }^{\prime }={\left\{{\omega }_j^{\prime }\right\}}_{j=1}^n$ can validate the signature provided that the distance between $\omega$ and ${\omega }^{\prime }$ is below a predefined threshold. Most of the existing FIBS schemes are based on the ROM. It is of great significance to design a FIBS scheme based on the SM. In this work, we adopt fingerprint minutiae as the biometric modality and present a feature extraction algorithm $\mathcal{E}$ that transforms raw minutiae into quantized, privacy-preserving attribute sets, and we present a False Rejection Rate (FRR)–False Acceptance Rate (FAR) trade-off framework to calibrate matching threshold t, with adjustable n for qualified error performance. Subsequently, we present a novel and efficient FIBS scheme, which is proven to be unforgeable in SM for any polynomially bounded adversary under selective identity attack model. Compared to the existing FIBS schemes based on the ROM, our new FIBS scheme has a strong security model. Compared to the existing FIBS scheme based on the SM, our new FIBS scheme reduces total computation consumption by approximately $33.55\%$ and achieves a significant reduction in communication consumption, saving approximately $68.07\%$ of the message and signature size, which is suitable for biometric authentication. Full article

Human gait datasets play a central role in the development and evaluation of computer vision models. However, the current dataset landscape remains highly heterogeneous, with inconsistent reporting of acquisition conditions, user variability, and sensing configurations, which limits reproducibility and hinders principled cross-dataset comparability. In this work, we propose a covariate-centered, modality-agnostic taxonomy for gait datasets, explicitly structuring variability across scene-level, user-level, and sensor-level factors. The proposed framework enables consistent characterization of datasets through a standardized set of covariates (A–R), bridging differences across application domains and sensing modalities. Following a systematic review protocol aligned with PRISMA 2020, we analyze 47 publicly available image- and depth-based human gait datasets spanning healthcare, biometric, and attribute-recognition application domains. Using the proposed taxonomy, we derive a quantitative analysis of covariate coverage, revealing systematic biases in current dataset design. Full article

Static, one-time authentication mechanisms such as passwords and PINs are increasingly inadequate for protecting mobile devices throughout an active session. Behavioral biometric continuous authentication (BBCA) addresses this gap by passively monitoring user-specific interaction patterns—keystroke dynamics, touch and swipe gestures, gait, and motion—to verify identity on an ongoing basis. This systematic review synthesizes 80 studies selected via a PRISMA-compliant protocol from IEEE Xplore, ACM Digital Library, Scopus, ScienceDirect, Web of Science, and SpringerLink (2017–2025). We examine behavioral and multimodal biometric modalities, machine learning approaches ranging from classical classifiers to deep sequence and transformer architectures, and their integration with intelligent personal agents, wearable devices, and IoT/edge infrastructures. Security analyses cover spoofing, adversarial and generative attacks, mimicry, and model-level threats including membership inference and reconstruction. Privacy-preserving mechanisms—cancelable biometrics, Bloom filter encodings, zero-knowledge proof protocols, federated learning, and blockchain-based identity management—are evaluated against practical trade-offs in energy consumption and latency on resource-constrained devices. Key research gaps are identified: the absence of standardized adversarial benchmarks, lack of end-to-end pipeline evaluations under simultaneous adversarial and privacy threat models, and limited user-centered studies on consent and acceptance of privacy-preserving mechanisms under frameworks such as GDPR. Recommended future directions combine adaptive multimodal fusion, privacy-preserving cryptography, energy-aware modality selection, and interdisciplinary human-centered evaluation to advance practical, resilient continuous authentication for mobile and assistant-enriched environments. Full article

With the advancement of contactless biometric technologies, improving recognition accuracy and robustness in unconstrained environments remains a significant challenge. To address insufficient feature representation caused by modality discrepancies, as well as non-compact feature distributions, we propose HDC-Net, a contactless palmprint and palm vein fusion recognition model based on a heterogeneous dual-stream network and supervised contrastive learning. Specifically, a heterogeneous dual-stream feature extraction architecture is designed to learn modality-specific representations from palmprint and palm vein images. Supervised contrastive learning is introduced to enhance intra-class compactness and improve inter-class separability. Furthermore, a cross-modal interaction fusion module is developed to facilitate complementary feature learning across modalities. Experimental results on Tongji, CASIA-MS, and the self-built SCAU-PM dataset demonstrate that the proposed method achieves equal error rates (EERs) of 0.05%, 0.21%, and 0.02%, respectively. These results indicate that the proposed method achieves reliable recognition performance across different datasets and provides a feasible approach for contactless palmprint and palm vein fusion recognition. Full article

Electroencephalography (EEG) has emerged as a promising modality for biometric user authentication due to its inherent uniqueness and resistance to spoofing attacks. Significant advances in brain wave signal analysis over recent years have reinforced its potential as a distinctive and reliable biometric trait. However, a comprehensive evaluation of the overall progress in this field remains limited. To address this gap, this paper presents an in-depth survey of EEG-based user authentication systems. The survey begins with a comprehensive overview of the human brain’s structure and functional organization, followed by a discussion of EEG signal acquisition principles and commonly used recording devices. It provides a detailed review of data acquisition protocols, publicly and proprietary available EEG databases, and essential preprocessing techniques required for effective signal refinement. The paper further examines feature extraction strategies and classification algorithms employed in EEG-based biometric authentication. In addition to reviewing existing methodologies, the survey identifies key challenges and future considerations in EEG biometrics, such as signal variability, age, mental health conditions, inter-session and inter-subject variability, etc, to establish stable and robust algorithms. This work serves as a foundational reference for researchers, outlining current progress and presenting a structured roadmap for future advancements in EEG-based biometric systems. Full article

Acoustic gait recognition is an emerging passive biometric modality that identifies individuals by unique walking sound patterns. This work presents a reproducible benchmarking framework for convolutional neural network (CNN)-based acoustic gait recognition, providing a systematic evaluation methodology across varying identity pool sizes. Raw footstep recordings from the AFPILD dataset were converted into 128-bin mel-spectrograms and used to train a compact CNN across identity pool sizes from 10 to 40 subjects. To ensure statistical reliability, a three-times-repeated five-fold stratified cross-validation protocol was implemented. Experimental results demonstrate strong discriminative capability, with validation accuracy reaching 94.92% and Equal Error Rate (EER) of 1.31% for the 40-subject configuration. A multi-seed subset validation experiment across five independent random subject draws per pool size confirmed that the observed scaling trend is consistent across subset compositions rather than an artifact of a single subject selection. Additional analysis confirmed the framework’s resilience to moderate environmental noise and its superiority over classical Mel-Frequency Cepstral Coefficients paired with a Support Vector Machine (MFCC-SVM) and Convolutional Recurrent Neural Network (CRNN) baselines, supporting the feasibility of acoustic gait recognition as a passive biometric modality. Full article

As micro, small and medium-sized enterprises (MSMEs) compete with limited resources, lightweight systems are needed to secure their digital assets. Fuzzy vaults (FVs) are useful for protecting secrets and, when applied to biometric systems, provide error-tolerance and privacy to enrolled biometric features. Combining multiple biometric traits also improves performance against attacks like spoofing in multimodal (MM) authentication systems. However, the design of the FV and the biometric-fusion method applied can limit the system’s effectiveness. This study systematically evaluates recent studies on FVs and MM systems and presents an up-to-date review to identify gaps, give directions for future studies, and, ultimately, improve the design of these systems. The research targeting MSMEs was carried out in two parts, with the first search focused on MM systems and the second on FVs, following the PRISMA guidelines. The main findings include the need to optimise the resource intensity of FV systems for the authentication of large numbers of individuals. It also found the need to make the model compatible with other biometric modalities as greater focus is on minutiae features. By reviewing these systems, we aim to foster the development of lightweight MM FV models to provide privacy and security in MSMEs. Full article

Multimodal biometric systems have become essential components of modern electronic identity and authentication platforms where robustness under real-world degradation is critical. However, opaque face masks impose severe facial occlusion and attenuate high-frequency spectral components. Conversely, transparent face shields introduce complex specular reflections and act as an acoustic channel distortion source. Addressing these asymmetric degradation challenges, this paper proposes a reliability-aware Dynamic Score Fusion (DSF) for multimodal biometric identification. The proposed method performs sample-level reliability estimation for both face and voice modalities at the input stage. This enables sample-wise adaptive weighting of modality scores based on their estimated reliability. The framework integrates an ElasticFace-Arc backbone for face recognition with an Emphasized Channel Attention, Propagation and Aggregation—Time Delay Neural Network (ECAPA-TDNN) for speaker identification. The proposed approach is evaluated on the FaciaVox dataset, comprising face images and voice recordings acquired under multiple face-covering conditions. Experiments under the Standard to Cross-Condition Protocol (SCCP) and Multi-Condition Protocol (MCP) demonstrate that the proposed DSF consistently outperforms conventional score-level fusion methods, including Weighted Sum Fusion (WSF) and Logistic Regression Fusion (LRF). It achieves average Rank-1 accuracies of 89.6% (SCCP) and 93.7% (MCP), with gains of up to 9.3 percentage points over these baselines. The reliability estimators further demonstrate strong predictive capability, yielding Area Under the Curve (AUC) values above 0.95 for both modalities in distinguishing correctly and incorrectly identified samples under the closed-set identification setting. These findings confirm that sample-wise reliability modeling provides an effective mechanism for enhancing multimodal biometric performance under challenging mask and shield conditions, supporting the deployment of robust AI-driven electronic identification systems. Full article

Deepfakes threaten sensor-based authentication systems, including biometric sensors, surveillance cameras, and IoT edge devices. Unimodal detectors remain vulnerable to modality-specific attacks. We propose a multimodal deepfake detection framework optimized for resource-constrained edge devices, featuring a novel cross-modal attention fusion mechanism with adaptive gating. The architecture combines enhanced Res2Net for audio, temporal 3D CNN with SE attention for video, and bidirectional cross-modal attention with quality-based gates. On our benchmark (5472 audio + 1842 video samples), the fusion model achieves 96.7% accuracy, 96.6% F1-score, 0.988 AUC-ROC, and 3.3% EER. Adversarial testing shows 92.3% accuracy under the Fast Gradient Sign Method (FGSM) attack. The model has a 30.3 MB footprint and runs at 20 FPS on edge hardware. Modality contribution analysis reveals adaptive weighting (72% audio for TTS forgery, 78% video for lip-synced attacks). Cross-dataset evaluation on FakeAVCeleb achieves 92.3% overall accuracy, confirming generalization. Full article

Fingerprint mosaicking—the process of combining multiple fingerprint impressions into a single master fingerprint—is an essential step in modern biometric systems, but it is prone to errors that can significantly degrade image quality. This paper proposes a deep learning-based approach to detect and score hard mosaicking artifacts in fingerprint images. Our method uses a self-supervised learning framework to train a segmentation model on large-scale unlabeled fingerprint data, eliminating the need for manual artifact annotation. The proposed model effectively identifies mosaicking errors, achieving high segmentation performance across multiple fingerprint modalities—contactless, rolled, and pressed—and proves robust to different data sources. We also introduce a mosaicking artifact score that quantifies the severity of detected errors and enables automated evaluation of fingerprint images at scale. Training and evaluation rely on synthetic artifacts, we therefore provide a qualitative comparison to real stitching failures and discuss the limits of this validation strategy in detail. By addressing the previously underexplored problem of reference-free hard-artifact detection in fingerprints, our work contributes to improving the accuracy and reliability of fingerprint-based biometric systems. Full article

Field-programmable gate arrays (FPGAs) are increasingly used to bring biometric recognition from cloud- or GPU-centric deployments to resource-constrained edge devices where latency, power, and privacy are critical. This paper surveys recent (2021–2025) FPGA and FPGA-SoC implementations across five widely deployed modalities: face, fingerprint, iris, speaker (voiceprint), and finger vein. For each modality, we summarize representative implementations and the performance figures commonly reported in the literature (e.g., accuracy or EER, latency/throughput, resource usage, and power), highlighting the algorithm–hardware co-design choices that enable real-time operation. Across modalities, successful designs repeatedly employ streaming/dataflow architectures, aggressive quantization and fixed-point arithmetic, reuse-aware buffering, and heterogeneous CPU–FPGA partitioning, often supported by high-level synthesis and vendor deep learning IP. Beyond throughput, we discuss how FPGAs facilitate privacy-preserving on-device processing and can integrate template protection and presentation attack detection within the same fabric. Finally, we identify open challenges related to scalability to larger models, memory-bandwidth constraints, and design productivity, and outline research directions enabled by emerging adaptive FPGA architectures and more automated toolflows. Overall, the surveyed evidence indicates that FPGAs are a compelling platform for deterministic, energy-efficient, and secure biometric inference at the sensor edge. Full article

Biometrics technology is undergoing a paradigm shift from static single-modal authentication to continuous multimodal sensing, combined with higher-performing algorithms powered by new deep learning techniques. This editorial reviews cutting-edge advancements and trends in the field of biometrics in four dimensions—novel sensors, modalities, algorithms, and equipment—as well as summarizes the contributions to this Special Issue, “New Trends in Biometric Sensing and Information Processing” by grouping them into the corresponding aspects of breakthroughs in this field. Full article

Recent advances in ear biometrics have yielded increasingly accurate detection and recognition methods, driven by the ear’s uniqueness and permanence as a non-invasive biometric modality. Nonetheless, several limitations persist, including computationally demanding models, inconsistent evaluation metrics, and portable systems restricted by manual capture and limited datasets. To address these challenges, we developed a lightweight, video-based ear biometric system implemented on the Raspberry Pi 5. The system integrates You Only Look Once Version 12 (YOLOv12) for ear detection, EfficientNet-4 for feature extraction, and k-Nearest Neighbors (k-NNs) for recognition. Its robust hardware platform combines Raspberry Pi 5 with the Raspberry Pi AI Camera and AI HAT+. To train, fine-tune, and optimize YOLOv12 and EfficientNet-4, we used the Visual Geometry Group (VGG)Face-Ear dataset for training and the Unconstrained Ear Recognition Challenge 2019 dataset for validation, with k-NN employed for classification. The system is evaluated for classification accuracy and system-level performance. 13 participants, comprising 10 enrolled and three unenrolled subjects, participated in testing the system. The enrolled participants registered in the system were correctly identified, whereas unenrolled participants were excluded and rejected. The system achieved 92.31% accuracy, 95.45% precision, 96.97% recall, and an F1-score of 0.95, confirming the feasibility of deploying advanced ear biometric methods on embedded, resource-constrained devices. Full article