Privacy-Preserving Integration of Face Recognition System and ESD Tester Using Federated Learning

Facial recognition technology has been widely used in various industries for identification and tracking purposes. However, the integration of facial recognition with Electrostatic Discharging testers is constrained by data security and privacy issues. To address these concerns, this investigation proposes a federated learning model approach for integrating facial recognition technology with ESD testers. The Integration of Facial recognition with ESD tester using federated learning model with Pre-FedAvg Algorithm preserves data privacy and security by using a distributed learning approach which maintains high accuracy and efficiency of the ESD testing systems. This research evaluates performance of the proposed approach metrics like Accuracy, Precision-recall, and F1 score. Results show that this approach outperforms conventional method while preserving data from various vulnerabilities. The electronic manufacturing industries, quality control departments, and safety monitoring sections are among the key areas of this strategy. It has the potential to revolutionize the way ESD testing is performed and enhances the safety and reliability of electronic devices and new dimensionality of features in factory processes like calculating over time of workers and making ESD proof.