Dynaface measures facial symmetry and facial movement from still images and video, using AI to place 97 facial landmarks automatically. It works on both symmetric and asymmetric faces, and every measurement can be exported to CSV/Excel for further analysis.
Dynaface is free and open source, and is developed by Jeff Heaton in collaboration with Johns Hopkins University. All processing happens locally on your own machine — no image or video data is uploaded anywhere. See the story behind Dynaface for background.
Get Dynaface
Recommended for macOS: an Apple M-series chip (Intel is still supported), 16GB+ of memory, and macOS 14 (Sonoma) or later. If the application will not start, the Mac support guide walks through launching it from Terminal and collecting log files for a bug report.
Documentation and Libraries
- User's Guide — the application manual.
- Python library — scriptable access to the same measurements.
- .NET library — for C# and other .NET applications.
- Source code — released under the Apache License 2.0.
How It Works
Dynaface builds on three neural networks, all run locally through ONNX Runtime:
| Model | Role | License |
|---|---|---|
| BlazeFace (short-range) | Face bounding-box detection | Apache-2.0 (MediaPipe) |
| SPIGA (WFLW-98) | 98-point landmarks and head pose | BSD-3-Clause |
| U²-Net | Background/saliency removal for lateral views | Apache-2.0 |
Research Using Dynaface
Dynaface has been used in peer-reviewed medical research to quantify oral-ocular synkinesis and to study how AI-derived facial metrics relate to patient-reported outcomes. If you use Dynaface in academic work, please cite:
- Renne, A., Heaton, J., & Boahene, K. D. O. (2026). Associations of AI-based facial metrics with patient-reported outcomes in idiopathic facial paralysis. Laryngoscope. Advance online publication. https://doi.org/10.1002/lary.70417
- Renne, A., Heaton, J., Derakhshan, A., Nellis, J. C., Desai, S. C., & Boahene, K. D. (2025). Use of dynamic, automated facial analysis in quantifying oral-ocular synkinesis. Facial Plastic Surgery & Aesthetic Medicine. https://doi.org/10.1177/26893614251395737
- Berges, A. J., Renne, A., Heaton, J., Leung, D. G., & Boahene, K. D. (2025). Facial weakness in facioscapulohumeral muscular dystrophy: Objective and patient-reported measures to guide reconstructive interventions. Facial Plastic Surgery & Aesthetic Medicine, Article 26893614251407675. https://doi.org/10.1177/26893614251407675
A BibTeX entry is available in CITATION.bib. Please also cite the original authors of the three neural networks listed above; their references are in the project README.
Privacy
Dynaface collects no data and no personal information. It is not designed to transmit image or video data to any external server, cloud platform, or third-party data center; all analysis runs locally. The only network access the application initiates is opening your web browser to view the online manual. All output — annotated images, CSV, and Excel exports — is written to locations on your own file system that you choose.
Dynaface is not a medical device
Dynaface is a research tool. It is not a registered medical device and is not intended to diagnose, treat, cure, prevent, or monitor any disease or medical condition; it provides informational facial symmetry measurements only.
AI-based measurements may contain errors, and can be affected by image quality, lighting, pose, facial expression, camera angle, and landmark detection accuracy. Always independently verify results before relying on them for clinical, research, or decision-making purposes.
Institutional requirements for clinical research — IRB approval, HIPAA considerations, and similar — are the responsibility of the researcher's institution and are not addressed by the Dynaface license.