Existing biometric systems are predominantly built upon 2D biometrics which are vulnerable to presentation attacks, and have a limited coverage of the biometric surface. 3D biometrics is emerging due to the rapid development of 3D sensing technology. 3D biometrics is effective in defending against spoofing attacks and potentially offer more robust performance under different conditions. However, there exist many challenges in developing effective 3D biometric systems in terms of 3D biometrics reconstruction and recognition. In this article, we present a systematic survey on the latest developments of 3D biometric systems guided by our proposed taxonomy of methods for 3D biometrics.

Urbanization and intensive anthropogenic transformation of natural habitats significantly influence avian breeding ecology, particularly in rapidly changing urban environments. Understanding species-specific reproductive responses to these pressures is essential for effective conservation planning. This study presents the first comprehensive analysis of the nesting ecology and breeding success of the Song Thrush (Turdus philomelos) in the Republic of Nagorno-Karabakh, focusing on Stepanakert city and its surrounding urban, suburban, and peri-urban habitats. Field studies were conducted during the breeding seasons from 2017 to 2023 across a range of habitat types, including parks, gardens, orchards, bushes, cemeteries, and suburban forests. Nest placement, nesting substrates, nest dimensions, egg characteristics, and breeding phenology were recorded using standard ornithological and biometric methods. Breeding success and fledging success were assessed across habitat categories. The results revealed clear habitat-related differences in nesting success. Breeding success ranged from 78.5% in urban parks to 94.4% in suburban forests. Fledging success was lowest in bush habitats (52.2%) and highest in urban forests (78.2%). Overall, 73.1% of chicks reached fledging age, and approximately 64% of the 1,277 recorded eggs resulted in mature juveniles. Breeding activity occurred in two main periods, with hatching primarily observed from early June onward. The findings demonstrate that song thrush exhibits considerable ecological plasticity, with higher reproductive success in less disturbed semi-urban habitats. These results highlight the importance of habitat structure and anthropogenic pressure in shaping breeding success and provide essential baseline data for the conservation and management of urban bird populations in the region. This study is particularly relevant as it provides the first quantitative evidence of how habitat type and anthropogenic pressure shape the breeding success and population ecology of song thrush in urban, suburban and peri-urban landscapes of Nagorno-Karabakh.

Face recognition has become a widely adopted biometric authentication method due to its convenience, non-intrusiveness, and ability to authenticate users in realtime. However, the widespread adoption of face recognition systems has also led to a surge in spoofing attacks, where attackers attempt to bypass security by using printed photographs, digital images, replayed videos, or even 3D masks. Traditional face recognition algorithms are unable to differentiate between genuine live faces and these spoofing attempts, which poses a critical risk to security systems in banking, mobile authentication, border security, and other sensitive applications. Therefore, ensuring that the detected face is live, a process known as face liveness detection, has become a crucial requirement for secure biometric authentication. Recent advancements in deep learning have provided powerful tools for solving complex image-based recognition tasks. Among these, Convolutional Neural Networks (CNNs) have demonstrated remarkable performance in image classification, object detection, and feature extraction tasks due to their ability to learn hierarchical features from raw images without manual feature engineering. This paper proposes a CNN-based approach for face liveness detection, designed to distinguish between live and spoofed faces with high accuracy and robustness under varied conditions, including different lighting environments, backgrounds, and facial orientations. The proposed system leverages CNN’s hierarchical feature extraction to capture subtle differences between real and fake faces that are often imperceptible to human observation, such as texture inconsistencies, reflection patterns, and pixel-level variations. The proposed method was evaluated using widely recognized datasets, including CASIA-FASD and Replay-Attack, which provide diverse scenarios and various types of spoofing attacks. Preprocessing steps include face detection, resizing, and normalization, along with data augmentation techniques such as rotations, flips, and brightness adjustments to improve the model’s generalization. The CNN architecture consists of multiple convolutional layers for feature extraction, pooling layers for dimensionality reduction, and fully connected layers for classification. The model is trained using the Adam optimizer with categorical crossentropy loss, and its performance is evaluated in terms of accuracy, precision, recall, and F1-score.

The responsible use of biometric recognition systems raises important questions about user acceptance, particularly regarding privacy concerns and the context in which these technologies are deployed. This study, conducted among young adults (N = 130) representing Generation Z, explores how users evaluate the acceptability of biometric recognition methods. A unique scenario-based design allowed us to examine whether the perceived benefits and risks of biometric methods (fingerprint and face recognition) remain consistent across different environments (workplace, leisure event, airport). The two-phase design first measured general acceptability across 10 biometric methods, then assessed perceived risks and benefits within contextualized scenarios. Results show that while fingerprint and face recognition are broadly accepted, their perceived risks and benefits vary significantly depending on the setting. Study reveals that fingerprint recognition is more sensitive to context with significant differences in 46% of tests than face recognition (25%).

Attendance management is an essential activity in educational and other environments. Conventional attendance management systems using manual attendance sheets, RFID cards, or even biometric methods like fingerprints face problems of accuracy, proxy attendance, hygiene issues, and higher maintenance costs. To overcome these problems, this paper proposes an intelligent attendance management system using virtual loggers with face recognition technology. In this paper, we propose an attendance management system using face recognition technology with the help of YOLOv8 face detection and FaceNet face recognition. The system is implemented using a Flask-based web server with a React-based web interface. SQLite is used to store attendance data. One of the major advantages of this system is that it includes an automated parent notification system. Parents would be immediately notified of their child’s attendance or absence. In this paper, we have also compared the accuracy of our system with other conventional attendance management systems. From the results, it is clear that our system is more accurate and scalable compared to other attendance management systems. It is also immune to proxy attendance. Hence, this system is very efficient and reliable

Global soft biometrics-based identification refers to the recognition of subjects using human traits such as gender, age, and ethnicity. Unlike traditional biometric methods that rely on unique physical markers such as fingerprints or iris scans, soft biometrics represents a non-intrusive, viable, and versatile approach, thus making them particularly valuable for surveillance and security applications. Despite significant advances, several issues have been associated with traditional biometrics, like maintaining accuracy, addressing algorithmic bias, and limited computational efficiency. To address those issues, this paper presents a comprehensive coverage of the current advances in Global soft biometric-based recognition as a solution, where four key contributions are made; i.e., (i) advocacy on the relevance and impact of soft biometrics in surveillance and security, (ii) development of a new and unique CeleBImg dataset to overcome algorithmic biases and improve diversity in soft biometric-based recognition, (iii) rigorous performance comparison of current methods in-practice for Global soft biometrics-based recognition and, (iv) identification of open challenges with potential solutions in the field within the context of surveillance and security. This paper sets a solid foundation for using Global soft biometrics in the CCTV-based surveillance and security domain, with their significance, relevance and effectiveness.

Biometric encryption integrates physiological traits with cryptographic operations to improve authentication security. Retinal vasculature is particularly attractive due to its internal protection, permanence, and high inter-subject variability. we present a revised and rigorously justified multidimensional retinal encryption framework that generates three independent keys—RDDM (Retinal Diagonal Distance Metric), ROTD (Radial Origin-Terminus Distance), and DRID (Diagonal–Radial Intersection Distance)—from a single retinal vessel map. This framework is intended as a biometric-driven key generation and strengthening module to enhance user authentication, rather than a standalone standard encryption algorithm. It operates under a threat model focused on resisting brute-force key guessing in controlled biometric contexts, but not advanced attacks like quantum cryptanalysis or side-channel exploitation. Retinal images undergo preprocessing (CLAHE, vessel segmentation, skeletonization, endpoint detection) to extract stable endpoints. These endpoints produce distance measures that are normalized and combined into polyalphabetic key streams. We provide stepwise derivations of the encryption E(x) and decryption D(y) equations, explicitly justify mod 124 as the symbol table size used in implementation, and include a detailed cryptanalytic evaluation (entropy, NIST SP800-22 randomness tests, Hamming distance, collision analysis, noise sensitivity, and Full-Space Key Guessing (FSKG) calculations). Experimental results on three retinal samples (n_vessels = 27,41,105) show substantially increased FSKG times and near-maximal key entropy relative to single-key baselines. Limitations and sensitivity to image quality are discussed.

Gestational age (GA) is essential for assessing fetal development, but conventional methods such as last menstrual period and ultrasound are often inaccurate, particularly in late pregnancy. Recent advances in deep learning (DL) and MRI offer more reliable and consistent GA estimation by capturing detailed fetal brain development. This study aimed to develop deep learning models for GA prediction using multi-view fetal brain MRI and to compare their performance with conventional biometric regression techniques. A total of 1,321 fetal MRI scans were used to train and evaluate various DL models, while an additional 80 publicly available MRI scans served as an external test set. Two training strategies were explored: transfer learning versus training from scratch, and single-view versus multi-modality input. The pre-trained ResNet-101 model achieved a mean absolute error (MAE) of 4.47days and a coefficient of determination (R2) of 0.96 on the internal test set. On the external test set, the model yielded an MAE of 6.57days, outperforming the biometric regression method, which achieved an MAE of 9.42days. Explainability analysis revealed that the model predominantly focused on the lateral ventricles, cerebellum, and surrounding brain regions for GA prediction. The integration of multi-view MRI and transfer learning significantly enhanced the predictive accuracy of DL models for GA estimation. The proposed approach outperformed conventional biometric regression and highlighted clinically relevant anatomical regions, demonstrating its potential for use in prenatal diagnostic applications.

Biometric methods hold significant promise for measuring consumer psychological responses to advertising, but the literature remains fragmented and lacks theoretical cohesion. To synthesize this growing field, the authors conducted a systematic bibliometric analysis of 216 articles (2000–2024), charting the intellectual structure of biometric applications in advertising research. Four distinct clusters emerged: (1) neurophysiological measurement and consumer cognition; (2) visual attention measurement via eye tracking; (3) consumer response measurement integrating biometric and traditional methods; and (4) advertising disclosure studies. Our analysis not only charts the evolution and current landscape but also maps the intellectual structure of the field to reveal how these methods are currently integrated into advertising theory. This synthesis highlights areas of theoretical connection and disconnection and outlines targeted directions for future work to improve the explanatory use of biometric data in studies of media influence and consumer behavior.

This study aims to determine the effects of environmental factors across different ecosystems on the anatomy of the medicinally important species Mentha longifolia L. and to reveal its adaptation mechanisms. Comparative analyses were performed using anatomical, microscopic, histochemical and biometric methods to clarify the extent and nature of anatomical variability in ecotypes of the species, thereby exploring their potential for environmental adaptation. Anatomical sections of the species were stained using histological reagents and permanent slides were prepared for subsequent analysis. This study represents the first comparative analysis of the ecological-anatomical characteristics of M. longifolia under in situ and ex situ conditions. Furthermore, statistical analysis of micrometric indicators confirmed the species’ climatic resilience and adaptive responses to stress. In the in situ ecotype, parenchymatic excretion, an active “punctate-porous” cellular structure in the rhizome and well-developed aerenchyma (in rhizome cortex - in situ: 51.51 ± 4.955 µm; ex situ: 43.29 ± 4.014 µm) were identified. In ex situ specimens, parenchyma cell size differences were statistically significant (e.g., in the leaf - in situ: 31.52 ± 2.279 µm; ex situ: 37.51 ± 2.465 µm). Additionally, variations were observed in the xylem lumen diameter (e.g., in the stem - in situ: 23.54 ± 1.664 µm; ex situ: 29.31 ± 2.252 µm). The structural adaptations revealed through comparative ecological-anatomical studies represent evolutionary advancements in plant anatomy and possess substantial scientific and practical relevance. This comprehensive research, systematically conducted for the first time on Azerbaijans’ flora, confirms the ecological plasticity of the species.

Precise biometric measurement of the mouse eye using optical coherence tomography based on optic-nerve-head imaging.

This paper proposes a novel radar-based framework for non-contact biometric identification through heart signal extraction, targeting secure and privacy-conscious identification scenarios. Traditional biometric methods, such as fingerprint and facial recognition, face challenges including privacy concerns, vulnerability to spoofing, and the requirement for close proximity or direct line-of-sight. Our framework addresses these issues by reconstructing electrocardiogram (ECG) signals from radar-extracted cardiac motion data and implementing an open-set person identification system. Specifically, the framework integrates ECGReconNet, a specialized deep learning model for reconstructing ECG signals from human chest wall displacement, the InceptionTime model enhanced with fixed-Class Anchor Clustering (fixed-CAC) loss for robust feature anchoring, and a hypersphere-based delineation method to differentiate known from unknown individuals. Experimental results on a public dataset demonstrate state-of-the-art performance, achieving 99.61% accuracy in closed-set identification (27 subjects) and 93.97% accuracy under challenging open-set conditions (14 known and 13 unknown subjects). However, the proposed approach exhibits limitations, including sensitivity to abrupt body movements and environmental noise, potential performance degradation under severe cardiac irregularities, and reduced efficacy with increased numbers of unknown identities.

In recent years, Electrocardiogram (ECG) biometric authentication has emerged as a hot topic in biometrics research due to its unique advantages including intrinsic aliveness characteristics and convenience for users. However, due to the non-stationary and nonlinear nature of ECG signals, there are still some challenges to be addressed for the application of ECG biometric authentication. In this paper, we propose a method that employs the short-time fourier transform (STFT) and a local binary descriptors learning method for ECG biometric authentication. Specifically, we first convert ECG heartbeats into two dimensional spectrogram images by STFT. Second, we extract pixel differential vectors (PDVs) from each point in the spectrogram images of the training ECG heartbeats. Third, we learn a projection matrix to map these PDVs into low-dimensional binary descriptors with three objectives: 1) The error between the original PDV and binary descriptor is minimized. 2) The intra-class variation of the local binary features is minimized and the inter-class variation of the local binary features is maximized. 3) The L2,1 norm of the learned binary descriptors is minimized. Finally, we represent each spectrogram as a histogram feature by clustering and pooling these binary descriptors. Experiments on the database verify that the proposed method outperforms other existing ECG biometric authentication methods in terms of performance.

Central Europe faces an overabundance of wild ungulates, which is driven by several factors, including traditional hunting practices. The harvest of females is insufficient and recorded without verification, even when they were not actually hunted. This practice contributes to further population growth through accurate hunting records. Therefore, basic procedures for automated registration based on muzzle pattern animal biometric evaluation of harvested wild ungulates were proposed. The red deer (Cervus elaphus) served as the model species. For the assessment of biometric characteristics, 2,193 photographs were taken from the frontal and overhead directions of 972 harvested red deer during regular game management. A comparison of the collected images using the LoFTR (Local Feature TRansformer) method revealed the potential for individual identification, with the peak accuracy of 95.048%. On the contrary, the minimum accuracy was 90.048% using a combination of overhead and frontal images of high and medium quality. Because there is no solution for the recognition of ungulates the comparison of these results was performed with the recognition systems for pets and livestock. Achieved accuracy is around 2% better than comparable recognition systems (with similar dataset size, number of feature points, etc.). The results confirmed that biometric methods can be used to identify and record harvested game. This can be achieved by developing a mobile application that transmits images for automated comparison and evaluation. Once individual identity is confirmed, the animal will be registered. This ensures a verifiable record of harvested game and provides a solid foundation for sustainable hunting planning.

Accurate identification of cattle and buffalo breeds is vital for livestock management, genetic conservation, productivity enhancement, and the implementation of national agricultural initiatives. Traditional identification techniques such as ear tagging, branding, and RFID are often invasive, error-prone, and inefficient in large-scale farm environments. Recent advancements in Artificial Intelligence (AI) and Computer Vision (CV) have enabled non-invasive, automated, and highly accurate livestock identification using image-based techniques. This paper presents a comprehensive review of image-based bovine breed recognition systems, analysing research published between 2018 and 2025. It examines the evolution from classical machine learning approaches to advanced deep learning models, including Convolutional Neural Networks (CNNs), transfer learning, attention mechanisms, object detection frameworks (YOLO), and video-based recognition systems. The review also highlights biometric identification methods such as muzzle pattern and facial recognition, lightweight architectures for edge deployment, and the integration of AI models with IoT-enabled smart farm management systems. Finally, key challenges related to dataset limitations, environmental variability, computational constraints, and adoption barriers are discussed, along with future research directions aimed at developing scalable, robust, and real-time AI-driven livestock identification solutions.

ObjectiveThe aim of this study was to determine the lip print patterns among adolescents from the Quechua and Suni ecological regions of Ancash, Peru, and to explore the relationship between the variables and their differentiation using logistic regression models.MethodsA quantitative, observational, prospective, cross-sectional, and analytical study was conducted. The sample comprised 192 adolescents from representative educational institutions, who requested the informed consent of their relatives. Personal and anthropometric data were recorded, and lip prints were obtained according to the conventional system of lipstick and adhesive tape using the classifications by Suzuki &Tsuchihashi and Renaud.ResultsThe population was predominantly male (55.2%) and more represented from the Quechua population (61.5%). Regarding their nutritional status, it was found that more than half were in average nutritional status (53.6%), although a significant proportion was overweight (41.8%). Regarding the Suzuki patterns, there was a predominance of types II (52.1–55.8%) and IV (50.5%), while the Renaud patterns presented a predominance of types G (49% in the upper left quadrant) and E (36.4–38.1%) in the lower quadrants. In the multivariate analysis, it could be identified that the only factor significantly associated with the Suzuki pattern was the geographical region. Adolescents from the Suni region presented this pattern more frequently than those of the Quechua population (60% lower odds, compared with Quechua adolescents: OR = 0.40; 95% CI: 0.22–0.73; p = 0.003). Sex, age, weight and height had no significant associations.ConclusionThe results indicate that lip print patterns have a characteristic dominant pattern in high Andean adolescents, with a significant influence of the geographic region on the morphology of the lips. The results underscore the significance of lip prints as a biometric method and offer proof of the morphological diversity of the Andean populations.

ABSTRACTBackgroundTraditional biometric systems are vulnerable to forgery, highlighting the need for secure alternatives. Electroencephalography (EEG) offers inherent advantages in liveness detection and antispoofing but typically requires external stimuli. We propose a novel paradigm leveraging intrinsic respiratory‐evoked EEG signals for identity authentication, with potential applications in clinical settings where unobtrusive monitoring is critical.MethodsWe developed a 64‐channel EEG acquisition system with synchronized respiratory event monitoring. Thirteen healthy volunteers performed four breathing patterns: oral, nasal, slow nasal, and rapid nasal breathing. A hybrid deep learning model was designed to optimize spatial–temporal feature extraction from EEG signals.ResultsThe model achieved 98.3% accuracy in identity recognition using rapid nasal breathing‐evoked EEG, outperforming traditional biometric methods. Nasal breathing patterns consistently yielded higher accuracy than oral breathing, with rapid nasal breathing showing the strongest discriminative power.ConclusionsRespiratory‐evoked EEG signals provide a viable, noninvasive biometric identifier. The high accuracy of rapid nasal breathing opens avenues for clinical integration, such as continuous patient authentication in respiratory monitoring devices or secure access to electronic health records.

Biometric security technologies are increasingly important for protecting sensitive information and securing access control. There are inherent problems related to spoofing, privacy and data security in traditional monomial biometric systems. In this paper, we proposed a novel deep learning framework to enhance the biometrics security by using multispectral face, iris and fingerprint information. Combining deep hashing into the proposed fusion framework, a strong binary multimodal latent representation is generated which is robust in presence of fake attempts. The proposed approach also integrates a hybrid security framework (combining cancellable biometrics and secure sketch method) for improving security of biometric templates. Furthermore, deep auto encoder algorithm is applied for feature extraction to get improved encoded features in order to boast security. The efficacy of the approach is demonstrated on a multimodal face, iris and fingerprint biometric database, resulting in improved performance along with enhanced privacy through cancelability and unlink ability of biometrics templates. Deep hashing function is also tested on an image retrieval dataset task as well standard one where the network structure could be applied’re used and it shows similar adaptability.

As mobile banking continues to grow at an exponential rate, the financial industry is faced with a critical challenge: How to keep user credentials secure without compromising on efficiency. Password-based authentication is still dominant but has major limitations which compromise both security and user experience. These systems are susceptible to the most common attack vectors such as phishing, malware and man-in-the-middle attacks, especially if users are using weak passwords or sharing passwords. Additionally, mobile devices have limited input interfaces that are frequently sources of frustration and error. As a result, there is increasing interest in other more secure and convenient alternatives such as biometric and multi-factor authentication (MFA) to mitigate the inherent weaknesses of password-based systems. This systematic literature review, which covers studies from 2020 to 2025, provides a critical review of biometric authentication methods used in mobile banking. It analyses existing approaches, security risks and implementation practices adopted by major banks across the world. While biometric systems are more secure and user friendly than traditional systems, they also introduce new challenges in terms of privacy, spoofing and regulatory compliance. The review gives a detailed overview of the current advances, key issues, and emerging research directions, which will give valuable insight to the development of secure and easy-to-use authentication systems in mobile banking.

New models quantifying tree volume, biomass, and carbon have recently been implemented across the USA, termed the National-Scale Volume and Biomass (NSVB) framework. Little research has been done to quantify the implications of these new models on the standing dead tree (SDT) carbon pool, which occupies a substantial portion of the nation's total forest ecosystem carbon stocks. This project compared predictions of carbon stocks in SDTs using the previous estimation approach (the Component Ratio Method) and NSVB using the most recent FIA data collected across the conterminous USA. Equivalence tests were conducted to compare predictions using the two modeling systems. Results show similar findings to what has been recently observed for live trees, namely that NSVB produces predictions of carbon in SDTs larger than those produced from CRM. However, predictions produced from NSVB and CRM for SDTs in advanced stages of decay (i.e., decay classes 4 and 5) are similar, likely due to the lack of tops and limbs in these SDTs, which has been suggested as a reason for the increased carbon stock predictions produced in live trees using the NSVB framework. Individual SDT predictions have important implications when scaled to the population (e.g., condition and state levels), where we similarly observed NSVB predictions to be larger compared to CRM predictions. These results highlight the role that biometrical methods play in determining carbon in SDTs, such as decay class and structural loss reduction factors and species-specific carbon fractions that are implemented in the NSVB framework.