Related Experiment Video
Updated: Jul 18, 2026
09:49
Holistic Facial Composite Creation and Subsequent Video Line-up Eyewitness Identification Paradigm
Published on: December 24, 2015
Effectiveness in Preventing the Elopement Using a Face Recognition System for Surveillance Camera Images
Satoru Sekine1, Kumiko Shokawa2, Hidenori Kato1
1Division of Medical Informatics, Tottori University Hospital.
Studies in Health Technology and Informatics
|May 17, 2025
Summary
Preventing unauthorized hospital departures is crucial for patient safety. This study improved patient tracking accuracy by combining surveillance cameras in hospital wards and entrances, significantly reducing false alarms.
Area of Science:
- Medical Informatics
- Computer Vision
- Patient Safety
Background:
- Unauthorized patient departures from hospitals pose significant risks to patient safety.
- Effective monitoring systems are needed to prevent such incidents.
Purpose of the Study:
- To enhance the precision of patient monitoring systems for preventing unauthorized hospital departures.
- To evaluate the effectiveness of integrating surveillance data from hospital wards and entrances.
Main Methods:
- Implemented a face recognition system utilizing surveillance cameras at two key hospital locations: the ward and the entrance.
- Registered 35 admitted patients for face recognition and performed face detection.
- Compared the precision rates of systems using only entrance cameras versus combined ward and entrance cameras.
Main Results:
- The precision rate using only hospital entrance surveillance cameras was low at 18.1%, attributed to environmental limitations.
- Integrating surveillance camera data from both the hospital ward and entrance achieved a precision rate of 81.0%.
Conclusions:
- Combining surveillance camera data from hospital wards and entrances significantly improves the accuracy of patient monitoring.
- The proposed integrated system effectively reduces false positives, enhancing patient safety by minimizing unauthorized departures.
