Electoral fraud, particularly multiple voting, undermines the integrity of democratic processes. To address this challenge, this study introduces an innovative facial recognition system that integrates an enhanced 50-layer Residual Network (ResNet50) architecture with Additive Angular Margin Loss (ArcFace) and Multi-Task Cascaded Convolutional Neural Networks (MTCNN) for face detection. Using the Mahalanobis distance, the system verifies voter identities by comparing captured facial images with previously recorded biometric features. Extensive evaluations demonstrate the methodology’s effectiveness, achieving a facial recognition accuracy of 99.85%. This significant improvement over existing baseline methods has the potential to enhance electoral transparency and prevent multiple voting. The findings contribute to developing robust biometric-based electoral systems, thereby promoting democratic trust and accountability.

Biometrics has been used in the Cameroonian electoral system for several years to improve voters’ identification by delivering voter cards. During the electoral phase, voters with voter cards are identified through a paper-based system at their polling stations. When the results are released, opponents loudly criticize the results citing electoral fraud. One of the issues of fraud to be resolved is multiple voting. To resolve this problem, this paper proposes a system that takes as input facial images from each voter using an enhanced ResNet50 architecture with ArcFace loss for facial recognition, and MTCNN for face detection, compares it with the recorded input features using Maha-lanobis distance, and produces results as output. Positive results imply that he/she can vote. After voting, the voter’s facial image is captured again and a short text message is delivered as confirmation from the system. A summary of the votes is produced which guarantees that a person has voted only once. This paper describes the methodology adopted to build the system. The facial recognition accuracy reached 99.85% which is an improvement compared to the baseline.