Search Results (292)

Visual impairment affects approximately 2.2 billion people worldwide, yet existing assistive technologies remain fragmented and prohibitively expensive. This paper presents Munir, an integrated multimodal assistive system designed to enhance human–computer interaction through a combination of a mobile application and Bluetooth-enabled smart glasses. Munir leverages a hybrid machine learning architecture to provide inclusive, real-time support for daily living activities. The system integrates ten core capabilities—including face recognition, optical character recognition, and scene description—all accessible through a unified bilingual (Arabic/English) voice interface. By employing on-device processing for biometric tasks, Munir ensures user privacy and trust while maintaining high responsiveness. End-to-end system evaluation on the SCface dataset achieves a 96.69% recognition rate with 0% False Accept Rate. At an estimated first-year total cost of $806, Munir demonstrates a 4–5× cost advantage over commercial alternatives, providing a scalable and affordable multimodal solution for global digital inclusion. Full article

Introduction: A diverse ichthyofauna is supported by the Lima River in northern Portugal. Despite its ecological significance, Ramsar-protected wetlands status and Natura 2000 site, the system remains among the least studied in the Iberian Peninsula. Objective: This study characterises the fish assemblage of the Lima River and some of its tributaries. It examines the composition and abundance of species, as well as key biological parameters, across the river’s freshwater and estuarine sections. Particular attention is given to the balance between native and exotic taxa, and to the threats facing the native ichthyofauna. Methodology: Between 2021 and 2023, 3242 individuals belonging to 15 species were sampled using fyke nets, trammel nets, and electrofishing at 13 sites along the river system. Results: Native species accounted for 51.1% of the total catch. This comprised resident freshwater taxa, such as Pseudochondrostoma duriense, Achondrostoma oligolepis, Luciobarbus bocagei, Squalius carolitertii, Cobitis atlantica, Gasterosteus aculeatus, and resident Salmo trutta, alongside diadromous species, namely Chelon ramada, Petromyzon marinus, Alosa spp., migrant Salmo trutta and Anguilla anguilla. Exotic species accounted for 48.9% of the total catch, with four non-native taxa being recorded: Lepomis gibbosus, Micropterus salmoides, Carassius auratus and Gobio lozanoi. This reflects the extent of the biological invasion pressure on this system. Analysis of the stomach contents of Salmo trutta revealed active predation of non-native species. Plastic debris was detected in 1.1% of Salmo trutta stomachs, which evidences that anthropogenic pollution has reached freshwater feeding habitats. The first recorded instance of the invasive nematode Anguillicola crassus in the Lima River, where 84.8% of the eels sampled exhibited moderate-to-severe swim bladder damage, highlights the vulnerability of native species to biological invasions. Conclusions: Biometric analyses and condition factors suggest that the fish community is under cumulative anthropogenic stress, caused by factors including river fragmentation due to three dams and traditional fishing weirs. The near-equal representation of native and exotic species in catches indicates that the freshwater fish community is under significant invasion pressure, which has direct consequences for the conservation of the native ichthyofauna. These findings establish a crucial baseline for the evidence-based management of an Iberian river system that is ecologically important but data-poor. Full article

Electroencephalographic (EEG) signals have been extensively studied for emotion detection and, more recently, as an alternative for biometric identification and authentication. Biometric methods based on physiological signals are a non-conventional approach for personal identification, and their study is currently considered an open research field. However, EEG-based biometric systems face several challenges, including the influence of emotional states, which can affect their performance. This study evaluates the effect of emotional states on the performance of an EEG-based biometric system. Four widely used databases for biometrics and emotion recognition (DEAP, MAHNOB, SEED, and LUMED-2) were selected for analysis. Feature extraction was performed using multiple strategies in the time, frequency, and time–frequency domains. The performance of various classifiers—support vector machine (SVM), random forest (RF), artificial neural networks (ANN), and k-nearest neighbors (K-NN)—was evaluated separately. Furthermore, stacking was used as a classifier fusion method. Explicit modeling of emotional states contributed to improving classifier performance. The best model based on classifier fusion achieved an accuracy of 95.73 ± 1.83%. These results indicate that incorporating information about emotional state into EEG-based biometric systems can contribute to the development of more robust and realistic identification solutions. 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

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

Social robots are systems designed to assist people across different fields. During their operation, they have to interact with people with different characteristics and necessities. Consequently, correctly recognising the user interacting with the robot facilitates the generation of a personalised experience that satisfies the user’s needs. In robotics, user recognition is typically based on face recognition from image processing and datasets that require retraining the network to include new users. However, some robots, such as pet-like companions, often lack a camera due to reduced dimensions, limited computational resources, or privacy constraints. Additionally, robots can occasionally encounter new users, requiring online recognition to provide a personalised interaction experience. To address these limitations, this article presents a user recognition system based on voice biometrics and dynamic clustering for adaptive social robots. We evaluate a set of open-source models for voice biometric extraction using different clustering algorithms to identify the best combination for our application. The resulting system is implemented in a pet-like robot companion that is used for the affective support of older adults, demonstrating its capacities in a real-world scenario. The system achieves more than $73\%$ accuracy in recognising users who had previously spoken to the robot and more than $71\%$ success in recognising new users who had not previously interacted with the robot and creating a personal profile for them. However, the system still detects noise, especially when the speaker has never interacted with the robot. Full article

Face recognition technologies are increasingly deployed in transport infrastructures to improve efficiency and security, but they raise significant privacy and data protection concerns. This study reviews how privacy-preserving face recognition techniques can address these challenges in real-world settings. Using a systematic literature review approach, the paper analyses research across technical, operational, and governance perspectives. The findings show that while advanced methods such as encryption, federated learning, and de-identification can reduce data exposure, they are rarely implemented in operational systems, which tend to prioritize performance and scalability. At the same time, governance-focused studies emphasize issues such as proportionality, accountability, and fundamental rights, often without clear links to technical solutions. Overall, the review highlights a fragmented landscape and a gap between research and practice, underscoring the need for integrated approaches that align privacy-preserving techniques with practical deployment constraints and regulatory requirements. Full article

Cross-age face analysis has emerged as an important topic in biometric recognition due to substantial facial appearance variations caused by aging. Nevertheless, most existing approaches primarily focus on face verification (1:1 matching) and frequently rely on explicit age annotations, which limit their applicability in large-scale retrieval scenarios. In this study, large-scale cross-age face retrieval (1:N matching) is investigated, and a Hybrid Metric Learning Framework (HMLF) is proposed to learn age-invariant and retrieval-oriented facial representations without requiring age labels. The proposed framework integrates Additive Angular Margin Loss (ArcFace) with supervised contrastive learning to enhance feature discriminability. Furthermore, a mixed triplet mining strategy is introduced to improve the effectiveness of hard sample selection. A memory bank-based InfoNCE formulation is incorporated to provide a large number of negative samples, and an uncertainty-based adaptive weighting scheme is designed to automatically balance multiple loss components during optimization. To better simulate realistic retrieval scenarios, an extended cross-age retrieval evaluation protocol is established. Extensive experimental results demonstrate that the proposed framework achieves superior retrieval performance across different backbone architectures. The results further provide systematic insights into the influence of backbone design, loss formulation, and optimization strategies on cross-age retrieval accuracy. Full article

Brazil, as one of the world’s leading fruit producers, faces increasing challenges arising from climate change, particularly in avocado cultivation, where excessive solar radiation and high temperatures impair plant metabolism, yield, and fruit quality. This study evaluated the use of a calcium and magnesium hydroxide-based sunscreen in mitigating heat stress in eight-year-old ‘Hass’ avocado trees. The experimental design was a randomized complete block design in a 4 × 8 factorial arrangement, with five replicates. Sunscreen applications were performed at full bloom and at the initial fruit development stage (18 mm). Leaf temperature, fruit drop rate, yield-related traits, fruit classification, and the percentage of fruit lesions were evaluated. Applications of the calcium and magnesium hydroxide-based sunscreen at concentrations of 3.0% and 4.5% (w/v) reduced leaf temperature and improved fruit biometric attributes compared to the control, although the maximum fruit diameter was achieved at the 2.6% concentration. The 4.5% sunscreen concentration reduced leaf temperature and fruit drop in ‘Hass’ avocado trees by 1.5 °C and 24.5%, respectively, compared with the control and decreased the percentage of small and damaged fruits. The application of sunscreen improved fruit weight and the percentage of fruits with higher market value, while the fruit diameter presented higher values at intermediate concentrations. Full article

Three-Dimensional (3D) face reconstruction from monocular Red-Green-Blue (RGB) imagery remains a fundamental yet ill-posed challenge in computer vision, with applications in biometrics, augmented reality/virtual reality (AR/VR), and intelligent visual sensing systems. While deep learning has significantly improved reconstruction fidelity and realism, existing surveys primarily focus on network architectures in isolation, often overlooking how sensing conditions, data acquisition protocols, and geometric calibration influence reconstruction reliability and evaluation outcomes. This paper presents a sensor-aware, end-to-end review of deep learning-based 3D face reconstruction and introduces a unified modular framework that connects sensing hardware, data acquisition, calibration, representation learning, and geometric refinement within a coherent pipeline. The reconstruction process is organized into four stages: sensor-driven acquisition and calibration, landmark estimation and feature extraction, 3D representation and parameter regression, and iterative refinement via differentiable rendering. Within this framework, we examine how sensor characteristics, calibration accuracy, representation models, and supervision strategies affect reconstruction accuracy, perceptual quality, robustness, and computational efficiency. We further synthesize the reported results across widely used benchmarks using both geometric and perceptual metrics, highlighting trade-offs between reconstruction fidelity and deployment constraints. By integrating sensing-aware analysis with architectural evaluation, this survey provides practical insights for developing scalable and reliable 3D face reconstruction systems under real-world conditions. Full article

Face recognition technology implemented on blockchain platforms enhances the security and integrity of face embeddings (the numerical representations extracted from facial images). However, it encounters unique privacy challenges due to the transparent and immutable nature of blockchains. Face embeddings hold sensitive biometric data that, once compromised, cannot be changed like conventional passwords. This study offers a new framework for using the Internet Computer Protocol (ICP), a decentralized blockchain platform, to implement CosPEEPChain (blockchain-secured privacy-preserving face recognition using eigenface perturbation and CosFace). CosPEEPChain integrates eigenface decomposition with local differential privacy (LDP) to ensure the privacy of face embeddings, CosFace for cosine margin learning’s discriminative ability on perturbed eigenface representations, and blockchain to ensure transparent and tamper-proof storage of face recognition models. We present CosPEEP (privacy-preserving face recognition using eigenface perturbation and CosFace), which shows substantial improvements and maintains consistent performance over baseline PEEP (privacy using eigenface perturbation), with a mean accuracy of 96.77 ± 0.85% and stability (std = 0.31–1.28%) across a range of privacy budgets ($ϵ\in [0.5,8.0]$) on the LFW dataset. Statistical significance testing confirms CosPEEP surpasses PEEP in 11/16 privacy budgets (p < 0.05) with a mean improvement of +1.92%. We also present ArcPEEP, which uses additive angular margin loss (ArcFace) to compare margin-based improvements. We verify the attributes of the models on the chain. In total, CosPEEPChain uses fewer cycles compared to the baseline ICP face recognition. 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

The current study proposes an improved DenseNet-based Sequential Multimodal Biometric Authentication System, involving face and ear modality for better human identification. The architecture is composed of three convolutional layers and two dense layers, which are optimized for obtaining the discriminative spatial representations in 200 × 200 pixel facial and ear images. Evaluation is performed based on strict 5-fold subject disjoint cross-validation data to ensure the unbiased assessment. The model proposed attained a steady classification accuracy of 97.1 ± 0.79%, and balanced values for Precision, Recall and F1-score under controlled validation conditions, while the Performance analysis including False Acceptance (FAR), False Rejection (FRR) and Equal Error Rate (EER) showed that the EER found is around 1.05% at the optimum operating value. Comparative experiments between parallel feature concatenation and sequential verification techniques show that the sequential framework yields decreased FAR, when compared to the parallel framework, without having a detrimental effect on overall accuracy, while the Statistical validation by analysis of variance shows that the incremental architectural improvements have a significant impact on performance improvements. Findings of this analysis show a “score distribution” that both “single-trait and traditional multifactor systems” exceed the presentation of a novel method for Nex-G authentication solutions. This study advances biometric security by demonstrating how multimodal fusion may address the increasing global demand for robust and privacy-aware authentication methods, thereby setting a standard for intelligent multimodal recognition systems. Full article

Access control systems rely increasingly on multimodal biometric and behavioral signals to enhance security and robustness against sophisticated attacks. However, when heterogeneous modalities provide conflicting evidence, such as valid biometric credentials accompanied by abnormal behavioral or acoustic patterns, traditional fusion strategies based on static thresholds or majority voting often fail, leading to false alarms or insecure authorization decisions. This paper addresses this critical limitation by proposing a contextual decision-making fusion framework designed to resolve conflicting multimodal evidence at the decision-making level. The proposed approach models access control as a decision-making problem in a context of uncertainty, where independent agents generate modality-specific evidence from authentication channels based on face, voice, and fingerprints. A centralized fusion mechanism integrates heterogeneous results using adaptive reliability weighting and contextual reasoning to resolve conflicts before operational decisions are made. Rather than treating each modality independently, the framework explicitly considers inconsistencies, uncertainties, and situational context when aggregating evidence. The framework is evaluated using public benchmarks, including VGGFace2, VoxCeleb2, and FVC2004, combined with controlled multimodal scenarios that induce conflicting evidence. Experimental results obtained under controlled contradiction scenarios show that the proposed fusion strategy reduces false alarms and improves decision consistency by approximately 18%. These results are interpreted within the scope of controlled multimodal simulations. Full article

With the rapid advancement of autonomous driving technology and the commercialization of Human–Machine Interface (HMI) services, camera-based systems for external environment perception are being extensively deployed. While comprehensive camera systems enhance safety and convenience, they simultaneously raise serious privacy concerns by collecting facial and biometric information of Vulnerable Road Users (VRUs) and passengers. Although facial anonymization technology has emerged as a key solution, the field currently faces a fundamental challenge: the absence of unified performance evaluation criteria. Existing studies employ disparate evaluation metrics, making objective inter-model comparison and performance verification difficult. This study proposes quantitative evaluation metrics and corresponding evaluation criteria that enable systematic and objective assessment of facial anonymization model performance. Through large-scale experiments, we developed quantitative evaluation metrics encompassing facial landmark variations, visual similarity, and re-identification prevention capability, and derived specific threshold values based on statistical methodologies. Furthermore, to validate the proposed evaluation criteria, we conducted systematic empirical assessments using models that adopt different technical approaches. The validation experiments showed that the evaluation criteria proposed in this study can be applied across models with distinct technical characteristics. This research is expected to contribute to resolving the heterogeneous evaluation criteria issues in existing studies by providing unified evaluation criteria. It may also support the development of privacy protection technologies in autonomous driving environments. Full article