Related Experiment Video
Updated: May 1, 2026
Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children
Published on: September 1, 2018
Infrared-based blink-detecting glasses for facial pacing: toward a bionic blink
Alice Frigerio1, Tessa A Hadlock2, Elizabeth H Murray3
1Human Physiology Section, Department of Pathophysiology and Transplantation, Università degli Studi di Milano, Milan, Italy; Facial Nerve Center, Carolyn and Peter Lynch Center for Laser and Reconstructive Surgery, Division of Facial Plastic and Reconstructive Surgery, Department of Otology and Laryngology, Massachusetts Eye and Ear Infirmary, Harvard Medical School, Boston.
This study developed an eyeglass-mounted infrared blink detection system for facial paralysis rehabilitation. The system reliably detects blinks, offering a promising trigger for facial pacing systems to restore movement.
Area of Science:
- Biomedical Engineering
- Rehabilitation Technology
- Ophthalmology
Background:
- Facial paralysis presents significant functional and aesthetic challenges.
- Facial rehabilitation using pacing and robotic technology holds potential but requires effective movement detection.
- Detecting healthy facial movements is crucial for triggering stimulated movements in unilateral paralysis.
Purpose of the Study:
- To evaluate a novel blink detection system integrated into standard eyeglasses.
- To assess the system's feasibility as part of a closed-loop facial pacing system.
- To determine the accuracy of blink detection during various gaze positions and facial expressions.
Main Methods:
- An infrared (IR) emitter-detector unit was attached to safety glasses to monitor the palpebral fissure.
- The system was tested on 24 healthy volunteers.
- Blink detection accuracy was compared against video-quantified blinks during repose, gaze shifts, and facial expressions.
Main Results:
- Blink detection using signal magnitude showed 100% sensitivity in forward gaze but false detections during downward gaze.
- Signal rate of change (first derivative) effectively distinguished blinks from gaze-related movements.
- During forward gaze, the system achieved 87% true positive blink detection, with errors primarily from partial eyelid closures and gaze shifts.
Conclusions:
- The developed blink detection system offers a reliable, noninvasive method for detecting eyelid closure.
- This technology serves as a viable trigger for closed-loop facial pacing systems.
- Future iterations will focus on improving accuracy by incorporating multiple sensors and optimizing frame design to minimize errors during facial movements.
