This week (ending Sep 20) we aligned on a web application as the primary UI, with an optional server path only if heavier models truly require it. We’re prioritizing an in-browser pipeline to keep latency low and deployment simple, while keeping a small Python fallback available. We also validated hand detection on iPad photos using MediaPipe Hands / MediaPipe Tasks – Hand Landmarker and found it sufficient for early fingertip landmarking.
On implementation, we added a simple browser camera capture to grab frames and a Python 3.9 script using MediaPipe Hands to run landmark detection on those frames. The model reliably detected one or two hands in our test images and produced annotated outputs.