Paper Details

Name: Bharath Yalagi & Sangeetha J
Country: India

Year: 2026
Volume: Volume No: 13, January, Year: 2026 (Special Issue)
Page Number: 248-259
DOI: https://doi.org/10.5281/zenodo.18978344

ABSTRACT:
Automatic age and gender prediction via facial recognition is an important feature in modern applications, such as personalized marketing, surveillance, and security systems. This work focuses on applying CNNs in order to learn
and extract automatically features from face images, doing away with manually engineered features. The system predicts age within certain ranges and accurately classifies gender, even under tough environments characterized by variable illumination, facial expressions, and occlusions. Using a diverse and labelled dataset, the model generalizes to unseen data while dealing with real-world complexities. Used Techniques like transfer learning and data augmentation enhance the robustness and accuracy of system. The suggested approach not only enhances the reliability of prediction but also shows significant promise for deployment in areas such as forensic investigations, demographic studies, and human-computer interaction. This novel approach is expected to provide a scalable and efficient framework for automated demographic analysis.

Keywords: Convolutional Neural Networks, ResNet, VGGNet, deep learning, data augmentation