<![CDATA[FaceVoting is an electronic voting system that employs facial recognition technology to authenticate voters, enhancing the security and efficiency of voting processes. This research showcases the integration of the Haar Cascade algorithm, renowned for its rapid and accurate object detection capabilities, tailored explicitly for face recognition in varied conditions. Through rigorous testing, the system proved highly effective at recognising faces across different distances, angles, and expressions despite some limitations in detecting obscured or unregistered faces. Extensive evaluations involved recording faces at 30 cm and 100 cm distances, yielding consistent detection scores of 0.2586751709411996, illustrating the system's robustness. Additionally, face recordings validated under varying angles demonstrated the system’s ability to maintain accuracy with minimal score variation, highlighting its adaptability to different voter positions. Further tests on diverse objects and facial expressions underscored the system’s precision in real-world scenarios, albeit with challenges in recognising non-human objects, other people’s faces, and partially obscured faces. About 96.5% of the 110 participants expressed satisfaction with the facial recognition feature, emphasising their confidence in its potential to secure and streamline the voting process. The study confirms the viability of facial recognition technology in e-voting systems, providing a substantial improvement over traditional methods in terms of accessibility, reliability, and fraud prevention, thereby supporting a more inclusive and transparent electoral process. ]]>
Copyrights © 2024
