Project hold as we work through some bumps in the road
Team Gleason is excited to announce Project Insight, the creation of an open dataset of facial imagery of people living with ALS, to help advance innovation in computer vision and broaden the input potential for connectivity and communication.
Existing computer vision and machine learning datasets do not represent the diversity of people with ALS. This results in issues with the accuracy of identifying breathing masks, ptosis (droopy eyelids), epiphora (watery eyes), and dry eyes due to medications that control sialorrhea (excessive saliva).
Team Gleason is investigating the use of diverse data with AI and the front-facing camera already present in most computing devices to predict where a person is looking on a screen. Project Insight has been made possible through a gift from the Microsoft.
For more information, see the Project Insight page on TeamGleason.Org.
This dataset of collected images and associated metadata is made available for machine learning researchers under the Open Data Commons Open Database License (ODbL) with an additional No De-Identification clause.
The dataset is too large to host in a Git Repository. To attain a copy of the dataset, please contact research@teamgleason.org. You will be provided an SSH key and SSH configuration information with which you will be able to copy data to your own location using either scp or rsync.
Data is contributed to the dataset owned by Team Gleason under the Project Insight Data Contribution Agreement license.