Computer vision & assistive technology
SocialSync
Exploring how real-time visual feedback can make social cues easier to understand.
Conceptual architecture illustration
The idea
A desktop prototype that analyzes facial expressions from a camera feed and presents visual feedback. Designed around an assistive use case for autistic people, the project combines a computer vision pipeline with profiles and session history.
Inside the build
- 01
Combined face detection with a TensorFlow expression classification model.
- 02
Separated interface rendering and model processing into dedicated threads.
- 03
Smoothed predictions across recent frames and added session summaries.