Tinnitus biomarkers video capture (VIDEO)

Mass Eye and Ear

Caption

The researchers utilized recent advances in computer vision and implemented an automated pipeline to quantify facial movements. A face mesh was fit frame-by-frame, with additional analysis of local image statistics. The pipeline highlights otherwise covert movements in the recording such as a nostril flare (2s), a jaw clench (3s), and an eyebrow twitch (4.5s).

Credit

Please credit Mass Eye and Ear

Usage Restrictions

Use with credit: Mass Eye and Ear

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.