Under the hood

How the sign-validation engine works

Every practice attempt runs through a computer-vision pipeline that turns a webcam recording into an accuracy score \u2014 all on your device.

01

On-device hand tracking

MediaPipe’s HandLandmarker detects 21 landmarks per hand from your webcam, running entirely in the browser — no video leaves your device.

02

Landmark normalization

Each frame is re-centered on the wrist and scaled by the distance to a stable knuckle, so hand size and position in frame never affect the score.

03

Rotation alignment

Frames are rotated to a common orientation, so the same hand shape scores consistently whether your hand is tilted, high, or low.

04

Motion sequence matching

Your recording is compared to the reference sign frame-by-frame using Dynamic Time Warping — an algorithm that elastically aligns two sequences even when performed at different speeds.

05

Speed-invariant scoring

The match cost is averaged over the actual aligned path length, so signing faster or slower than the reference no longer changes your accuracy score.

06

Facial expression scoring

A face landmarker extracts blendshape coefficients — eyebrows, mouth, eyes — and compares them to the reference, since expression carries meaning in BSL.

Two-handed signs are scored against primary and secondary reference hand sequences, with a graceful fallback when only one hand is shown.

Ready to start signing?

Sign in or create an account and try Signwise for yourself.

Test the app
Signwise