Jul 2026· 2026 5th International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE)· pp. 1-7· 0 citations· 22 references
Abstract
Face recognition is a cornerstone in computer vision with its applications covering emotion analysis, healthcare and human computer interaction. This paper gives a complete explanation and classification of face recognition models by categorizing into Machine learning (ML), Deep Learning (DL) and hybrid techniques. Traditional methods rely on manual features and statistical evaluations that are relevant, whereas DL methods used convolutional and transformer-based techniques for classification and feature extraction. The integration of both techniques (hybrid) with its benefits performs better flexibility and more consistency for different conditions. This survey presents current innovations such as fuzzy similarity measures, self-distillation methods, segmentation improved Convolutional Neural Network (CNNs) and securely preserving quaternion networks. Applications including masked face detections, light variation enhancement and emotion-aware music recommendation is specified. The comparative analysis of cited works indicates that while DL models achieve superior recognition accuracy (typically >90% on benchmarks like FER-2013), they demand extensive data and computational resources, resulting in higher inference latency compared to hybrid models. Additionally, privacy concerns are an important challenge in multimodal biometric systems. This paper shows research gap in existing methods and demonstrates the demand for face recognition systems that are fast, protect user privacy and adjust with different environments for practical real world scenarios.
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
The study’s objective is to create a facial recognition system that is both lightweight and effective for secure biometric identification using MobileNetV3, and to assess how well it performs in comparison to more conventional, computationally demanding models. Group 2 (Intervention) refers to a MobileNetV3-based face recognition system with 30 samples and 98% confidence, while Group 1(control)relates to Conventional CNN based facial recognition models with 30 samples but low accuracy To guarantee high-quality inputs, data preprocessing methods like image alignment and normalization are employed. The model’s judgment are interpreted using SHAP (Shapely Additive Explanations), which also detects biases and identifies real inputs from fake attempts, such as images and movies, liveness detection techniques are used. When compared to conventional models, the MobileNetV3-based system achieved a far higher accuracy of 95% in facial recognition tasks. The system showed a Multi-Modal with 98% accuracy and low latency, which makes it appropriate for real-time applications. Transparency was greatly increased by SHAP-driven insights, which offered concise justifications for model choices. This study shows that the lightweight MobileNetV3-based facial recognition system outperforms conventional models in terms of accuracy, security, and explainability.
S.Hamsanandhini, K.S.Manojee, P.Palanisamy et al.· 2026 4th International Confe...· 0 citations
Image classification is a major area in computer vision, driven by rapid advances in deep learning. Over the last decade, convolutional neural networks (CNNs) and their variants have achieved high performance in applications such as medical diagnosis, autonomous driving, industrial inspection, remote sensing, and biometrics. However, choosing the right model remains challenging due to trade-offs between accuracy, computational cost, efficiency, and robustness. This paper presents a comparative study of different deep learning architectures, including classical CNNs, deep hierarchical models, residual and dense networks, and compound-scaled architectures. Using a common evaluation framework and standard datasets, the study analyzes performance based on key design factors such as depth, width, receptive field, skip connections, and normalization. Theoretical concepts like convolution operations, residual learning, and optimization are also discussed.The results show that deeper networks provide better representation, while residual connections and compound scaling improve training stability and efficiency. Lightweight models perform well in resource-limited and real-time environments. Overall, the study offers practical guidance for selecting suitable architectures and highlights future research areas such as neural architecture search, self-supervised learning, and efficient model deployment.
Riyaz Mohammed· International Journal of App...· 0 citations
The COVID-19 pandemic highlighted the importance of face masks as an effective non-pharmaceutical intervention for reducing the transmission of infectious diseases. Monitoring mask compliance in public environments such as hospitals, educational institutions, transportation hubs, and workplaces remains a challenging task when performed manually. Recent advances in computer vision and deep learning have enabled the development of automated face mask detection systems capable of operating in real time. This paper presents a comparative study of three deep learning architectures, namely a Custom Convolutional Neural Network (CNN), VGG16, and MobileNetV2, for face mask detection. The study employs a publicly available dataset containing 12,000 facial images categorized into mask and no-mask classes. Data preprocessing techniques including resizing, normalization, and augmentation were applied to improve model generalization. Experimental results demonstrate that MobileNetV2 outperforms the other architectures, achieving an accuracy of 98.7%, precision of 98.4%, recall of 99.0%, and an AUC-ROC score of 0.99 while maintaining real-time performance. The proposed system was further integrated with OpenCV for live video stream analysis. The findings indicate that lightweight transfer learning models offer an effective and practical solution for real-time face mask detection in resource-constrained environments.
Ruksar Fatima, Shaista Fatima· International Journal of Sci...· 0 citations
Facial Emotion Recognition (FER) has emerged as an important field of study in the field of computer vision with various applications in human-computer interaction, affective computing, healthcare monitoring, intelligent surveillance systems, etc. This work provides a comparative analysis of three types of Deep Learning architectures, i.e., a custom Convolutional Neural Network (CNN), a VGGNet-inspired architecture, and a Residual Network (ResNet), for the seven-class emotion classification task in FER2013 benchmark dataset. To make sure a fair comparison, all models were trained in identical experimental conditions under the same optimizer, learning rate, batch size and preprocessing strategy and callback configuration, so that performance differences could be attributed to different architecture variations only. The FER 2013 is a set of 35887 grayscale facial images with resolution 48 × 48 and are labeled in Angry, Disgust, Fear, Happy, Sad, Surprise and Neutral categories. Experimental evaluation shows that the model based on VGGNet has achieved the highest test accuracy of 81.23% with a loss of 1.67, 7.18 million parameters. The ResNet model achieved an accuracy of 78.45% with only 3.05 million parameters, which is a reduction of 57% in the model size with a negligible performance drop. The accuracy of the baseline CNN was 59.71% accuracy. In addition, a Streamlit-based real time web application to perform ensemble inference among the three models was created. The results provide practical advice for the choice of suitable architectures for FER, especially in cases where either computational or latency constraints are prevalent.
Sudharani Bandlapalli, Manasa Kamineni, Srihari Malineni et al.· 2026 6th International Confe...· 0 citations
Face recognition systems are widely used in surveillance, biometric authentication, access control, and digital identity verification; however, supervision sensitivity, evaluation stability, and performance consistency across datasets remain insufficiently understood. This study investigates the behavior of convolutional, transformer-based, and hybrid face recognition architectures under both Softmax and ArcFace supervision using five-fold subject-disjoint cross-validation on the Labeled Faces in the Wild (LFW) and FAGEv2 datasets. ResNet50, MobileNetV3, DeiT-Small, and a Hybrid multi-branch architecture integrating complementary convolutional and transformer feature representations were evaluated using Top-1 identification accuracy, Area Under the ROC Curve (AUC), Equal Error Rate (EER), computational complexity, and fold-level statistical analysis. Experimental results revealed substantial supervision sensitivity across architectures and datasets. On the LFW dataset, Hybrid-Softmax achieved the highest Top-1 identification accuracy (62.4%), while DeiT-Small-Softmax achieved the strongest verification performance with an AUC of 0.905 and EER of 0.159. On the FAGEv2 dataset, Hybrid-Softmax and DeiT-Small-Softmax achieved the highest identification accuracy (38.0%), while Hybrid-Softmax achieved the strongest verification performance with an AUC of 0.825 and EER of 0.251. Fold-level analyses demonstrated that the effect of ArcFace supervision varied across architectures and datasets, with consistent improvements observed for some convolutional architectures but not for transformer-based or hybrid models. Cross-dataset evaluation further revealed changes in model ranking and supervision behavior, indicating that comparative performance is strongly influenced by dataset characteristics and evaluation conditions. The findings demonstrate that additive angular margin supervision does not universally outperform conventional Softmax optimization and highlight the importance of multi-dataset benchmarking, fold-level evaluation, and supervision sensitivity analysis for robust and reproducible face recognition benchmarking.
Andisani Nemavhola, C. Chibaya, Serestina Viriri· Frontiers in Artificial Inte...· 0 citations