Harnessing Diversity in Face Recognition: A Voting and Bagging Ensemble Approach

Facial recognition plays a crucial role in various applications, as it tackles challenges such as changes in lighting, position, and facial expressions. This study aims to explore the effectiveness of ensemble learning methods, specifically the voting classifier and bagging classifier, in enhancing the accuracy of face recognition. We extensively examine our ensemble technique, leveraging the diversity that emerges from combining multiple classifiers. The voting classifier showcases superior accuracy (0.91), underscoring the effectiveness of blending numerous models. The bagging classifier, even though it has achieved a respectable accuracy of 0.72, demonstrates a noteworthy improvement compared to individual classifiers. These findings emphasize the effectiveness of ensemble learning in alleviating the challenges encountered in face recognition tasks. Improving facial recognition systems in real-life situations is one useful piece of advice that this research offers, as it advances our knowledge of ensemble learning.