Intelligent Facial Age and Gender Analytics Using Deep Learning

Facial expression recognition using a non-exclusive learning search-Fossa optimization algorithm with a convolutional neural network

Facial expression recognition (FER) is the process of detecting and identifying human emotions based on facial movements and visual cues. It analyzes facial regions, particularly the eyes and mouth, to recognize expressions such as fear, anger, and joy. However, recognizing facial expressions from images remains challenging due to variations in illumination, head orientation, and individual facial characteristics. In this research, a non-exclusive learning search-Fossa optimization algorithm integrated with a convolutional neural network (NELS-FOA-CNN) is proposed to select the most relevant features for accurate FER. In the conventional FOA, NELS is incorporated to enhance the exploration of the solution space, thereby facilitating the identification of optimal solutions and reducing the likelihood of becoming trapped in local optima. A CNN is employed for FER to learn spatial hierarchies of facial features and capture local patterns, such as textures and edges, that are useful for distinguishing among different facial expressions. A baseline graph convolutional network (GCN) is used to compare and validate the performance of the proposed NELS-FOA-CNN. The proposed NELS-FOA-CNN achieves accuracies of 95.80%, 71.23%, and 69.36% on the Real-world Affective Faces Database (RAF-DB), AffectNet-7, and AffectNet-8, respectively, demonstrating improved performance compared with the baseline GCN.

Integrated Facial Identity Verification and Expression Intelligence Using Video Streams

The increasing adoption of computer vision and artificial intelligence has created new opportunities for developing intelligent systems capable of understanding human facial behavior in real time. Facial expression analysis plays an important role in applications such as human– computer interaction, smart surveillance, healthcare monitoring, attendance management, and security systems. This paper presents a webcam-based facial expression detection and person recognition system that combines facial identification with emotion classification in a single framework. The proposed system first allows users to register by capturing facial images along with personal information and storing the extracted facial features in a trained recognition model. During real-time operation, the webcam continuously detects faces, identifies registered individuals, and predicts their facial expressions, such as happiness, sadness, anger, surprise, fear, disgust, and neutral state. The integration of face recognition and expression analysis enables simultaneous identification of the individual and interpretation of emotional responses without requiring manual intervention. The developed application provides a simple graphical interface for user registration, model training, and live expression recognition, making it suitable for practical deployment in educational institutions, workplaces, healthcare environments, and public monitoring systems. Experimental observations demonstrate that the proposed framework performs reliable real-time face detection and expression classification while maintaining efficient processing speed and recognition accuracy. The system offers a practical, scalable, and cost-effective solution for intelligent facial analysis using standard webcam devices.

Deep Learning-Based Face Detection, Feature Extraction, and Face Recognition from Video: A Comprehensive Review

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.

A hybrid approach to facial expression classification using appearance-based filters

Adaptive Face Recognition and Emotion Analysis Framework (AFREAF): A Real-Time Multi-Modal Deep Learning System for Comprehensive Facial Attribute Detection

This paper presents the Adaptive Face Recognition and Emotion Analysis Framework (AFREAF), a comprehensive, real-time system for simultaneously detecting and analysing multiple facial attributes, including age, gender, and emotional states. AFREAF integrates advanced deep neural networks with adaptive preprocessing techniques, including face alignment via MediaPipe landmarks and histogram equalisation to enhance feature extraction. The framework employs OpenCV's DNN module for robust face detection, specialised convolutional neural networks for age and gender classification, and the FER+ model for emotion recognition. A novel temporal smoothing algorithm ensures prediction stability across video frames. Experimental evaluation demonstrates that AFREAF achieves real-time performance at 28.4 FPS while maintaining competitive accuracy rates of 68.5% for age estimation, 94.2% for gender classification, and 71.3% for emotion recognition. The modular architecture facilitates easy integration into diverse applications, including human-computer interaction, security systems, and behavioural analytics.

Explainable Age and Gender Classification Using CNN with SHAP Interpretability on Human Facial Images

Many practical applications, for example, social media analysis, targeted marketing, human–computer interactions, and security systems, become possible through the reliable and accurate identification of a person, in terms of their gender and age, based on a photo of their face. The paper involves giving an end-to-end solution for online deployment that utilizes convolutional neural networks (CNNs) and explainable artificial intelligence (XAI) methods to classify age and gender in real time. The model uses Adience data and data augmentation to learn and cope with the imbalance in classes of age and gender. The CNN design uses convolutional, pooling, and fully connected layers to identify features, compress the input, and connect to the eight-age and gender-category classification target output branches. Several metrics may be used to gauge the efficacy of a model, including recall, F1-score, accuracy, and precision. Visualizing the impact of face traits on prediction results is possible using the SHapley Additive exPlanations (SHAP) approach, which does not sacrifice model quality or user trust. The web platform is built on a Flask framework to enable users to input facial images to the system and get an immediate prediction with explanations of the prediction provided in SHAP format. The usage of XAI proves the effectiveness and explainability of artificial intelligence use in the real-life context. Through experimental results, it is found that the model is highly accurate and explainable and hence is suitable to be used in real-life applications.   Received: 31 October 2025 | Revised: 14 July 2026 | Accepted: 5 August 2026   Conflicts of Interest The authors declare that they have no conflicts of interest to this work.   Data Availability Statement The data that support the findings of this study are openly available on Kaggle at https://www.kaggle.com/datasets/ttungl/adience-benchmark-gender-and-age-classification.   Author Contribution Statement Patel Alpaben Rameshbhai: Conceptualization, Methodology, Software, Validation, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Amisha Shingala: Formal analysis, Resources, Data curation, Writing – original draft, Visualization, Supervision.