Face recognition has become a pivotal application in computer vision, offering diverse applications from security to user authentication. This study explores the utilization of Convolutional Neural Networks (CNN) for enhancing the accuracy and efficiency of face recognition systems. CNNs, a subset of deep learning techniques, have demonstrated remarkable capabilities in processing and recognizing complex patterns within images.The research delves into the historical context of face recognition, tracing its evolution from traditional methods to the current state-of-the-art CNN approaches. It emphasizes the pivotal role of CNNs in handling intricate facial features and their ability to learn hierarchical representations, making them particularly adept at discerning subtle nuances in facial expressions.The experimental phase involves training the CNN model on extensive datasets encompassing diverse facial characteristics. The study meticulously evaluates the model's performance in terms of accuracy, speed, and robustness across various scenarios, including different lighting conditions and facial poses