This paper presents a novel hybrid face recognition system integrating Local Binary Patterns Histogram (LBPH), Neural Networks (NN), and Fuzzy Logic for real-time attendance tracking. The system leverages LBPH for efficient feature extraction, neural networks for advanced face classification, and fuzzy logic to handle uncertainties in the recognition process. The system was evaluated on a dataset of 15 participants, with 20 recognition attempts per individual, under varying conditions such as lighting, facial expressions, and facial orientations. The hybrid approach achieved an accuracy of 73.3%, with precision, recall, and F1-scores of 0.80 each, significantly outperforming systems that use LBPH or neural networks alone. The response time of the hybrid system averaged 1.2 s, making it suitable for real-time applications. Additionally, the fuzzy logic component reduced the number of false positives and false negatives, improving the system’s overall reliability. The results demonstrate that the proposed hybrid system is scalable, robust, and capable of adapting to various real-world conditions, ensuring accurate attendance logging in real-time scenarios.