Skip to content

Side
Projects

Things I build for fun.
Here's a select few that are in a complete enough state to share.

conf: 0.88[x: 0, y: 0]

// project_detected [0.96]

project_detected [0.96]

Real-Time Face Blur for Privacy-Preserving Video

A real-time face-blurring system that redacts faces in live and recorded video while keeping chosen identities visible. The modular pipeline combines YuNet/SCRFD detection, SORT tracking, SFace recognition, and configurable blur options for flexible speed-accuracy tradeoffs. On crowded IRL Twitch footage, it runs faster than real time on CPU and favors privacy by accepting a few extra blur boxes rather than missing a face.

PythonOpenCVYuNetSCRFDSORT
detections: 6
[x: 1280, y: 720]
demo_feed [live]00:12:34
input_stream_0 / 30fps / 1280x720conf: 0.97
git log --oneline

// signal_detected [0.91]

signal_detected [0.91]

HeartPal - the Arrhythmia Detecting Stethoscope

An end-to-end cardiac monitoring system combining a custom hardware stethoscope device, a Flutter mobile app, and a deep learning backend. The device uses a MEMS microphone connected to the phone's audio jack, while the app enables patients and doctors to record, share, and analyze heart sounds in real time. The ML pipeline employs bidirectional LSTMs with transfer learning from ECG to PCG data, achieving 98.8% accuracy in detecting arrhythmia, with high specificity to minimize missed diagnoses.

PythonTensorFlowFlutterFirebaseSignal ProcessingHardware
bpm: 72
[freq: 44100 Hz, ch: 1]
---

// agent_detected [0.93]

agent_detected [0.93]

Google Snake RL Gymnasium Environment

[grid: 20x20]

A Gymnasium environment that interfaces directly with Google's web-based Snake game, emulating a human player through computer vision. Captures the game state from the browser in real time, processes it into observations, and allows RL agents to train and run inference as if playing through the UI. Supports configurable grid sizes and reward shaping for training agents end-to-end.

PythonGymnasiumReinforcement LearningComputer Vision
reward: +1.0
// more_coming_soon

I'm (sometimes) working on something new. Check out my GitHub for the latest, or see the research page for the more 'serious' work.

Browse all repos