Face detection is an important technology in the field of pattern recognition and digital image processing that is widely used in various applications such as security systems, surveillance, and identity recognition. This study aims to develop a deep learning-based face detection system using the Convolutional Neural Network (CNN) architecture. CNN was chosen because of its ability to automatically extract important features from images through an in-depth training process. This system is designed using a diverse facial dataset to ensure model generalization to various lighting conditions, viewing angles, and facial expressions. The training process is carried out by applying data augmentation and parameter optimization techniques to improve detection accuracy. The evaluation results show that the developed CNN model is able to detect faces with a high level of accuracy, and demonstrates stable performance against input variations. The advantage of this method lies in its ability to detect faces in real-time with low latency and resilience to background noise. With the results obtained, this system is expected to be applied in various computer vision-based applications such as automatic attendance systems, intelligent surveillance, and biometric authentication. This research contributes to the development of more reliable and efficient face detection technology with a modern deep learning approach.