A survey of demographic attribute estimation from periocular images, covering publicly available datasets, methodological trends from handcrafted descriptors to deep learning architectures, and the state of the art in gender, age, and ethnicity prediction is provided.
Abstract
Soft-biometric attributes such as gender, age, and ethnicity provide valuable ancillary evidence when full identity recognition is not feasible, supporting applications in forensic investigation, identity verification, surveillance, or detection of synthetic and manipulated media. Among biometric modalities, the periocular region is a robust source of soft-biometric cues, as it often remains visible when other parts of the face are occluded, a frequent condition in forensic evidence and surveillance footage, and can be captured across a wide range of acquisition conditions. In this paper, we provide a survey of demographic attribute estimation from periocular images, covering publicly available datasets, methodological trends from handcrafted descriptors to deep learning architectures, and the state of the art in gender, age, and ethnicity prediction. We discuss use cases relevant to multimedia forensics and disinformation-detection applications, including demographic filtering in surveillance footage, age verification, and the detection of demographic inconsistencies in synthetic data. We also highlight open challenges, including dataset bias, cross-domain generalisation, fairness, ethical aspects, and the lack of forensic-oriented benchmarks.
In forensic environments, automated identification of perpetrators is difficult due to pose changes, changes in light, occlusion, and lack of labeled data. This paper presents ForensicNet, a lightweight deep learning framework for forensic face recognition that enhances attention. The suggested model combines the MobileNetV2 backbone with Convolutional Block Attention Modules (CBAM) to improve the learning of discriminative features while maintaining computational speed. A two-phase transfer learning strategy with adaptive layer unfreezing is used to improve domain adaptation and reduce overfitting. This study used publicly available datasets such as LFW and SCFace, with 15,000 facial images spanning 68 identity classes. The proposed model outperforms baseline architectures such as AlexNet, ResNet-50, and MobileNetV2, with an accuracy of 92.4%, a precision of 90.8%, and a recall of 89.5%. Additionally, the framework requires only 2.1 GFLOPs per inference, and hence can be used in real-time forensic surveillance applications.
S. N. J., L. B. T.· Engineering, Technology &...· 0 citations
Biometric identification is a vital feature in digital forensics, and unimodal systems of biometric identification, like face, voice, or fingerprint recognition, tend to experience poor performance under a contaminated situation or when complete. In this paper, a novel deep multimodal biometrics framework called ForensicNet is presented, which combines heterogeneous biometric modalities: face images, speech signals, and fingerprint patterns into a combined expression of robust forensic identity attribution. The architecture will be defined based on joint representation learning, deep fusion with an attention-based weighting layer, and an adaptive reliability module that recalibrates decisions when one or more biometric sources are partially unavailable. For evaluation, extensive experiments were performed on the three standard data sets: forensic face recognition, speaker verification, and fingerprint matching. The results suggest that ForensicNet achieves 19.3 percent higher identification accuracy than the unimodal baseline and conventional fusion baseline, a 22.7 percent lower equal error rate (EER), and 16.8 percent better robustness to missing modalities. Furthermore, ForensicNet can obtain these benefits while using 13.1 fewer computational overheads. Overall, the above results have proven ForensicNet to be a promising, scalable, reliable, and energy-saving forensic tool for practical law enforcement, border security, and digital identity verification solutions.
Karam Abdullah, Mohammed Khaldoon Altalib, Yahya Qasim Ibrahim· JOIV: International Journal...· 0 citations
A comparative analysis of existing studies is presented to highlight the evolution of deep learning techniques and their effectiveness in improving recognition accuracy and computational efficiency and emerging research directions are outlined to provide insights for future research.
Patel Bhautika Ronak· International journal of res...· 0 citations
Digital identity verification has become essential across online banking, e-governance, healthcare, education, and e-commerce. While biometric systems such as facial recognition, fingerprint scanning, and iris detection enhance convenience and scalability, they remain vulnerable to spoofing attacks including photo/video replays, deepfakes, silicone masks, and display-based presentation attacks. Liveness detection has therefore emerged as a critical security layer to distinguish genuine biometric traits from fraudulent representations. This paper presents a comprehensive study of liveness detection models, covering architecture, algorithms, and performance evaluation. It examines active and passive techniques, including texture analysis, motion cues, physiological signal extraction, and deep learning approaches. Traditional handcrafted features are compared with CNNs, RNNs, and transformer-based models. Emphasis is placed on multimodal biometrics and challenge-response mechanisms to counter advanced GAN-based deepfake attacks. A systematic framework is proposed, encompassing data acquisition, preprocessing, feature extraction, model training, and decision fusion, supported by mathematical formulations for classification, loss optimization, and evaluation metrics. Experimental results on benchmark datasets demonstrate improvements in accuracy, FAR, and APCER, with hybrid deep learning models integrating temporal and physiological cues outperforming single-modality methods. The paper concludes by addressing deployment challenges, ethical considerations, and future directions such as privacy-preserving learning, federated identity systems, and explainable AI security, offering a scalable approach for secure digital identity verification.
Salma El-Sayed· International Journal of App...· 0 citations
The increasing need for reliable human identification systems in secure environments has exposed the limitations of unimodal biometric systems. Individual biometric modalities, including fingerprint, face recognition, and iris scanning, are prone to noise, hardware limitations, spoofing attacks, and data acquisition errors, resulting in high false acceptance and false rejection rates. This paper presents a comprehensive framework for human identification using multi-biometric fusion of iris and face dynamics using a deep learning paradigm. By holistically combining the noise-free properties of the iris with the nonintrusive and globally accessible properties of facial features, the proposed system overcomes the fundamental limitations of unimodal biometric systems while harnessing their complementary benefits. The framework encompasses systematic data acquisition in various environmental settings, sophisticated preprocessing techniques involving normalization and augmentation, robust feature extraction using convolutional neural networks, and multi-level fusion techniques at the feature, score, and decision levels. Experimental results show that the proposed fusion strategy outperforms unimodal biometric systems in recognition accuracy, with a rate of accuracy above 99% and lower error rates. The proposed system is designed for critical applications in banking security, border protection, healthcare, and law enforcement, where identification accuracy and system integrity are paramount.
Shaik Badulla, Vundavalli Balasankar, G. L. V. Prasad· 2026 7th International Confe...· 0 citations
Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition while preserving utility for downstream tasks. With the rising emphasis on data privacy and responsible AI, face De-ID has emerged as an active research area spanning computer vision and privacy-preserving communities. Early approaches, and many contemporary ones, operate in the digital domain by modifying pixel-level or appearance-level features through post-capture processing. Recent advances extend face De-ID beyond post-processing by integrating privacy mechanisms directly into sensors during image acquisition, bridging sensing systems and downstream vision algorithms. In parallel, physical-domain methods explore wearable accessories and materials that conceal identity information in real-world environments prior to capture. In this survey, we present the first unified overview that spans the full data acquisition pipeline, encompassing the physical, sensor, and digital domains. Through this domain-centric lens, we systematically analyze current methodologies, technical progress, and the distinct challenges inherent to each stage. We then review and organize existing evaluation protocols, examining current practices and highlighting the critical need for standardized, comprehensive benchmarks. Finally, we identify key open problems and outline emerging research directions to guide future work in this rapidly evolving field. To support ongoing research, we maintain a project page that organizes relevant literature with collected datasets and open source code: https://github.com/CV-AC/Awesome-FaceDe-ID.