STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Operating Systems Development & Trends

Face Recognition Systems: An Anti-spoofing and Liveliness Verification Toolkit

  1. Vishwajeet Patil
  2. Samved Mantri
  3. Anish shah
  4. Saurabh Patil
  5. Abhaysinh Bhosale

Abstract

The safety of facial recognition technology is vital in the current digital era. In this research, a deep learning approach to face spoofing detection is presented, covering the complete process from data collection to real-time application. To guarantee model robustness, a 7,000-image bespoke dataset that includes both “real” and “fake” facial scenarios is curated. The YOLO architecture, a state-of-the-art object identification model, is used after necessary preprocessing. The model, which was developed using Google Colab's GPU, is enhanced with a confidence threshold to produce accurate predictions. After being trained, the model is incorporated into a real-time application that gives users a confidence score for dependability and color-coded visual indicators to distinguish predictions. The system successfully detects face spoofing, highlighting the potential of deep learning to strengthen facial recognition security. By combining data science and software development, this work offers a comprehensive approach to face spoofing detection, promising improved security for facial recognition systems.

Keywords

Support