Preventive Attendance Record using Photo from Mobile Phone and Printed Paper using CNN

Wisesa, Bradika Almandin
Mahat Putri, Vivin
Faristasari, Evvin
Jasman Duli, Sirlus Andreanto
Agustin, Silvia

J-Intech (Journal of Information and Technology)
Vol 13 No 01 (2025): J-Intech : Journal of Information and Technology

Face-based attendance systems are increasingly popular for their ease of use, but they are susceptible to fraud, such as using photos or videos for unauthorized attendance. This study introduces a digital attendance system that combines facial recognition with liveness detection powered by Convolutional Neural Networks (CNN). Liveness verification is achieved by analyzing subtle movements and responses to ambient lighting. The dataset includes 30 facial images, encompassing both authentic and fraudulent samples. Testing demonstrates a facial recognition accuracy of 91.3% and effective spoofing detection in static and dynamic settings. This system provides a secure, fraud-resistant attendance solution ideal for educational and corporate settings. Further enhancements are suggested to improve performance across diverse facial expressions and lighting conditions.