Despite its advances, face recognition (FR) technology confronts significant challenges, especially in adverse conditions such as varying lighting, facial expressions, poses, and aging effects, which necessitate the development of more robust and accurate recognition algorithms. The importance of face recognition for social robotics lies in its ability to facilitate personalized and secure interactions, enhancing the robot’s social engagement and functionality. This research introduces a novel FR methodology integrating statistical learning and shallow neural networks to refine facial feature representation and recognition. Our approach, which combines a Sparse Auto-Encoder with Exponential Discriminant Analysis, is evaluated across renowned face databases (GT, AR, LFW), demonstrating superior recognition rates and outperforming existing state-of-the-art techniques. Specifically, our system achieved recognition accuracy of 91.94% on the AR dataset under sunglass occlusion, 90.04% under scarf occlusion, and an impressive 99.74% on the LFW database, highlighting its efficacy and resilience against challenging conditions. This work not only advances the field of facial recognition but also underscores the potential of integrated machine learning approaches in addressing complex real-world challenges in digital authentication and security.