The National Crime Records Bureau (NCRB) reports that between 2016 and 2021, an average of 3.4 lakh people in India were reported missing, indicating that the long-standing problem of missing persons has reached concerning proportions. This is equivalent to 930 people per day or 39 people per hour. At the same time, big cities like New Delhi, Chennai, and Mumbai have seen a sharp increase in their surveillance infrastructure; New Delhi leads the world in this regard, with an astounding 1,826.58 cameras per square mile. To address this, we implemented a system that makes use of the latest developments in computer vision, particularly the FaceNet and MultiTask Cascaded Convolutional Neural Network (MTCNN) algorithms. Our mission is to use the vast potential of surveillance technology and minimize the increasing number of missing person cases. Our approach uses behavioral analysis and facial recognition to build a robust and effective system that can identify missing people from photos or videos, even when there are multiple people involved. We see our suggested solution as a revolutionary means of addressing the pressing social issue of missing people, guaranteeing a more prompt and precise response enabled by cutting-edge technology.

1. Ivan Grishchenko, Artsiom Ablavatski, Yury Kartynnik, Karthik Raveen-dran, and Matthias Grundmann. Attention mesh: High-fidelity face mesh prediction in real-time, 2020.
2. Jiankang Deng, Jia Guo, Jing Yang, Niannan Xue, Irene Kotsia, and Stefanos Zafeiriou. ArcFace: Additive angular margin loss for deep face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10):5962–5979, Oct 2022.
3. Gurlove Singh and Amit Kumar Goel. Face detection and recognition system using Digital Image Processing. In 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), pages 348–352, 2020.
4. G. B. Huang, T. Berg, and E. Learned. LFW Face Database. https://vis-www.cs.umass.edu/lfw/, n.d. Computer Vision Lab.
5. S. Winkler. resources. vintage - resources. https://vintage.winklerbros.net/facescrub.html, 2021, March 23. Retrieved November 14, 2023.
6. Chunming Wu and Ying Zhang. 2021. MTCNN and FACENET Based Access Control System for Face Detection and Recognition. Autom. Control Comput. Sci. 55, 1 (Jan 2021), 102–112. https://doi.org/10.3103/S0146411621010090
7. Khan, Soumya & Sengupta, Diganta & Ghosh, Anupam & Chaudhuri, Atal. (2023). MTCNN++: A CNN-based face detection algorithm inspired by MTCNN. The Visual Computer. 1-19. 10.1007/s00371-023-02822-0.
8. N. Singh and R. M. Brisilla, "Comparison Analysis of Different Face Detecting Techniques," 2021 Innovations in Power and Advanced Computing Technologies (i-PACT), Kuala Lumpur, Malaysia, 2021, pp. 1-6, doi: 10.1109/i-PACT52855.2021.9696583.
9. Raju, Anand & Saravanan, Thirukkumaran & Arul, Jawahar. (2022). AI based face recognition system using FaceNet deep learning architecture. AIP Conference Proceedings. 2640. 020031. 10.1063/5.0118073.
10. Li H, Hu J, Yu J, Yu N, Wu Q. UFaceNet: Research on Multi-Task Face Recognition Algorithm Based on CNN. Algorithms. 2021; 14(9):268. https://doi.org/10.3390/a14090268
11. Qi, S., Zuo, X., Feng, W. and Naveen, I.G., 2022, December. Face Recognition Model Based On MTCNN And Facenet. In 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC) (pp. 1-5). IEEE.
12. M. Alansari, O. A. Hay, S. Javed, A. Shoufan, Y. Zweiri, and N. Werghi. Ghostfacenets: Lightweight face recognition model from cheap operations. IEEE Access, 11:35429–35446, 2023
13. Pham, T.N., Nguyen, N.P., Dinh, N.M.Q. and Le, T., 2022, November. Tracking Student Attendance in Virtual Classes Based on MTCNN and FaceNet. In Asian Conference on Intelligent Information and Database Systems (pp. 382-394). Cham: Springer Nature Switzerland.
14. Xu, X., Du, M., Guo, H., Chang, J. and Zhao, X., 2021. Lightweight facenet based on mobilenet
15. Gu, M., Liu, X. and Feng, J., 2022. Classroom face detection algorithm based on improved MTCNN. Signal, Image and Video Processing, 16(5), pp.1355-1362

FaceNet Face Recognition MTCNN Missing Person Detection Convolutional Neural Network Facial Embeddings