HYBRID CNN-VGG19 MODEL FOR REAL-TIME FACE RECOGNITION SYSTEM

Abstract

Face recognition is a pivotal task in computer vision, with applications ranging from security to biometric authentication. Convolutional Neural Networks (CNNs) have emerged as a cornerstone in advancing face recognition technology by enabling automatic feature learning directly from raw pixel data. Additionally, the VGG19 architecture has garnered attention for its depth and remarkable performance in various visual recognition tasks. In this paper, we propose a hybrid model that combines the strengths of CNNs and VGG19 for face recognition. Leveraging the hierarchical features learned by CNNs and the depth of VGG19, our hybrid model aims to achieve enhanced accuracy and robustness in facial recognition tasks. We present a detailed exploration of the model architecture, training methodology, and evaluation metrics, demonstrating its effectiveness through experimental validation on standard face recognition datasets. Our findings suggest that the CNN+VGG19 hybrid model outperforms standalone CNNs or VGG19 architectures, showcasing promising advancements in face recognition technology. This research contributes to the ongoing efforts in developing efficient and reliable face recognition systems, with potential implications for various real-world applications.