Facial Matching and Reconstruction Techniques in Identification of Missing Person Using Deep Learning

Abstract

The number of missing person cases has dramatically increased nowadays, leaving loved ones with a lot of unanswered questions. Police inquiries and public announcements are two regularly used traditional methods for locating missing persons, although they frequently fall short, especially over time. Artificial intelligence (AI) is gaining popularity and could be used to enhance the search process. This study offers a revolutionary approach for solving the unsolved cases of missing individuals by using AI-based facial matching and face reconstruction approaches. The proposed method successfully uses the ORL (Olivetti Research Laboratory) Dataset's Support Vector Machine (SVM) classifier to reach an outstanding accuracy of 93% by combining face landmarks and machine learning algorithms. Additionally, a 3D face reconstruction method based on Convolutional Neural Networks (CNN) trained on the varied 300-W dataset achieves a high accuracy of 90%. These results demonstrate the potential of AI and deep learning models for improving missing person identification. The proposed approach offers a viable option that aids in providing closure to the impacted families, making a significant contribution to the field and reducing crimes in the future.