Press Kit

1. About the research
2. Images, captions, credits
3. Publication
4. Frequently asked questions
5. People
6. Video
7. Contact

1. About the research

   Devices that facilitate nonverbal communication typically require high computational loads or have rigid and bulky form factors that are unsuitable for use on the face or on other curvilinear body surfaces. Here, we report the design and pilot testing of an integrated system for decoding facial strains and for predicting facial kinematics. 

   The system consists of mass-manufacturable, conformable piezoelectric thin films for strain mapping; multiphysics modelling for analysing the nonlinear mechanical interactions between the conformable device and the epidermis; and three-dimensional digital image correlation for reconstructing soft-tissue surfaces under dynamic deformations as well as for informing device design and placement. In healthy individuals and in patients with amyotrophic lateral sclerosis, we show that the piezoelectric thin films, coupled with algorithms for the real-time detection and classification of distinct skin-deformation signatures, enable the reliable decoding of facial movements. The integrated system could be adapted for use in clinical settings as a nonverbal communication technology or for use in the monitoring of neuromuscular conditions.

2. Images, captions, credits

   Downloadable file of images, captions and license information.

3. Publication

   Learn more here.

4. Frequently asked questions

   More information about this research is available in ourFAQ.

5. People

   Canan Dagdeviren
   Assistant Professor of Media Arts and Sciences
   LG Career Development Professor of Media Arts and Sciences
   Principal Investigator, Conformable Decoders research group

   Lin Zhang

   Farita Tasnim

   David  Sadat

6. Video

   Video credit: David Sadat and Ellen Long

7. Contact

   MIT Media Lab Communications
   press@media.mit.edu