AI-Based Missing Person Identification Using Deep Learning and Facial Recognition

Finding people who have gone missing is a very important problem for both the public and police. The usual ways of looking – manually going through lots of pictures and reports – take a long time and aren’t usually very good when there are big collections of images and information from the public. This paper describes an AI Missing Person Identification System, which uses deep learning and computer vision to find and pair faces in pictures people put in, with the faces in a database of people reported missing. The system combines face finding, getting the key features of faces, and comparing how alike faces are, all using convolutional neural networks. There is a website which lets people put up photos, put in reports about missing people, and do the automated matching. Testing showed the system is very good at finding matches, even if the light, how the person is turned, or the picture’s size isn’t ideal. This is a cheap solution, can be increased in size, and is good for organisations and the community to use.

Missing person detection, facial recognition, deep learning, computer vision, AI search system, image matching

1. Schroff et al., FaceNet: A Unified Embedding for Face Recognition [Google Scholar] [Crossref]

2. He et al., Deep Residual Learning for Image Recognition [Google Scholar] [Crossref]

3. Zhang et al., MTCNN Face Detection [Google Scholar] [Crossref]

4. Ultralytics YOLO Models [Google Scholar] [Crossref]

5. OpenCV Face Recognition Documentation [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet