Paper Contents
Abstract
Facial recognition has become a critical application of computer vision, with widespread use in security, healthcare, and authentication systems. However, achieving high accuracy often requires substantial computational resources and large annotated datasets, posing challenges for developers with limited resources. This paper presents an efficient facial recognition system leveraging transfer learning with the VGG-16 pre-trained deep convolutional neural network. The model is fine-tuned for face detection and recognition tasks, significantly reducing the need for extensive training datasets. The proposed system integrates advanced data augmentation techniques and is deployed as a user-friendly web application using FlaskDjango. Experimental results demonstrate the model's high accuracy in recognizing faces, even in constrained environments. This research highlights the potential of combining transfer learning and web technologies to create scalable, accurate, and accessible facial recognition solutions.
Copyright
Copyright © 2024 Akash Gite. This is an open access article distributed under the Creative Commons Attribution License.
