A rapidly evolving field of research, face recognition has gained considerable attention in recent years due to the wide range of applications it can be used for, including security, surveillance, and access control. One of the major challenges of face recognition is achieving accurate and reliable results, especially in complex and uncontrolled environments. To address this challenge, researchers have proposed various techniques for enhancing face recognition performance which include feature extraction and classification methods. Although these techniques have shown promising results, they heavily rely on the selection of appropriate hyperparameters to achieve optimal performance. Hyperparameters significantly impact the machine learning models, and selecting the optimal values for these hyperparameters is challenging. Traditional methods for hyperparameter tuning, such as grid search and random search, are computationally expensive and time-consuming, especially when dealing with high-dimensional parameter spaces. To overcome these limitations, metaheuristic algorithms have been proposed as an effective and efficient approach for hyperparameter tuning.