This paper presents an intelligent and automated framework for multi-face detection, recognition, and real-time blurring in video sequences under realistic and complex conditions. The proposed system was developed and evaluated using a locally constructed dataset that includes significant variations in illumination, background complexity, facial pose, and crowd density. To effectively manage scene complexity, a deep learning-based approach was adopted for robust feature extraction and classification. The dataset was divided into 80% for training and 20% for testing, and the model was trained for five epochs to ensure computational efficiency while maintaining high performance. The proposed framework was evaluated using standard performance metrics to measure detection and recognition accuracy. Experimental results demonstrate that the system achieves a recognition accuracy exceeding 90% in complex real-time scenarios involving multiple individuals. Furthermore, the automatic face blurring module achieved a 100% success rate in protecting detected identities within the tested samples. The main contribution of this work lies in integrating detection, recognition, and privacy-preserving blurring into a unified intelligent system capable of operating in real-time environments. The proposed framework shows strong potential for practical applications in surveillance systems, security monitoring, and video data privacy protection.