Finding Missing Person using Machine Learning

The increasing number of missing person cases worldwide has created a need for efficient and automated identification systems. Traditional methods of identifying missing individuals rely heavily on manual verification, eyewitness reports, and police investigations, which are often time-consuming and prone to human error. This paper proposes an intelligent Missing Person Detection System based on deep learning and facial recognition technologies. The proposed system utilizes FaceNet and Convolutional Neural Networks (CNNs) to extract facial embeddings from images and video streams. Face detection is performed using MTCNN and OpenCV, while cosine similarity is used for matching extracted features against a centralized database of missing persons. The system supports real-time identification through CCTV surveillance and uploaded images. A Flask-based backend and React-based frontend provide efficient communication and visualization of results. Experimental analysis demonstrates that the proposed approach achieves high recognition accuracy and low latency, making it suitable for deployment in public surveillance environments. The system can assist law enforcement agencies and humanitarian organizations in locating missing persons more effectively and reducing response times.