Multiple Face Recognition Surveillance System with Real-Time Alert Notification using 3D Recognition Pattern

• Published in: 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM ) pp. 1 - 6
• Main Authors: Dela Cruz, Jennifer C., Garcia, Ramon G., Hernandez, Sarah Mae A., Melliton B. Medina, John, Rose, Mary, Ostique, T., Santos, Angela Mae A., Verdadero, Marvin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-11-2019
• Subjects: 3D Face Recognition Pattern; Cameras; Face; Face recognition; Haar Cascade; Iterative Closest Point (ICP); Iterative closest point algorithm; Multiple Face Recognition; Position Map Regression Network (PRN); Real-Time; Surveillance; Three-dimensional displays
• DOI: 10.1109/HNICEM48295.2019.9072871

This paper presents a surveillance system that can detect multiple persons and provides a notification once a banned person is detected. A person is banned once the system matches its face from the faces registered in the database. The system uses Haar Cascade to detect faces from the surveillance and Iterative Closest Point (ICP) to match the detected faces from the database. Position Map Regression Network is also used to construct the 3D models of the detected faces. The researchers tested the system for the process time of matching, the maximum angle the system can process, detection of faces given different conditions of occlusions, and detection of faces given different distances. The matching accuracy of the surveillance system is 90% and the fastest process time is 1 second.