Face recognition technologies are rapidly becoming integral to a variety of applications, ranging from security systems to user authentication. This increasing reliance necessitates robust and accurate methods for face liveness detection. This paper presents and thoroughly evaluates two cutting-edge methods for face liveness detection: the Restrictive Voting approach and the Transfer Learning Approach. Our evaluation was performed using the Replay-Attack dataset. Various performance metrics were reported, including Accuracy, Precision, Recall, and F1-Score. Additionally, a comparative analysis was presented specifically for Half Total Error (HTER) and Equal Error Rate (EER), clearly indicating the superior performance of both methods compared to current state-of-the-art techniques. Remarkably, both methods achieved a zero False Acceptance Rate (FAR), thereby entirely negating the possibility of unauthorized access. These groundbreaking findings not only affirm the robustness of the introduced methods but also suggest their substantial potential for implementation in high-security, real-world scenarios, highlighting their unmatched excellence in face liveness detection.