SELECTED WORKComputer vision & assistive technology

PROJECT NOTE

SocialSync

Exploring how real-time visual feedback can make social cues easier to understand.

Conceptual system illustration
ROLE
Full-stack development lead
CONTEXT
Team assistive-technology prototype
YEAR
2024
TOOLS
Python, OpenCV, TensorFlow, PyQt5, Flask, MySQL

The work behind the system.

A team desktop prototype exploring visual feedback for autistic people interpreting social cues. It connects camera-based expression classification to a PyQt5 interface and a Flask/MySQL profile backend. Supporting screens include demonstrations; clinical outcomes were not established by this project.

What I focused on

  1. 01

    Combined face detection with a TensorFlow expression classification model.

  2. 02

    Separated interface rendering and model processing into dedicated threads.

  3. 03

    Smoothed visual feedback using confidence-weighted recent detections.

PythonOpenCVTensorFlowPyQt5FlaskMySQL