Surface-signal instrument

Not a verdict.
A record of change.

One photograph tells you very little. Lighting, camera and time of day move the pixels more than your body does. So we built the opposite of a one-shot reading: an instrument that learns what your usual range looks like, then reports only what moved beyond it.

01 — The order of operations

We remove you before we read anything.

De-identification is not a policy we promise. It is a step that happens first, in the pipeline, before any model sees the image.

01

Your face is removed

The face is masked and the tongue is segmented out of the frame. Metadata is stripped. What continues down the pipeline is a surface, not a person.

02

The capture is graded

Blur, exposure and framing are scored before analysis. A capture that can't support a reading is rejected rather than guessed at.

03

Surface signals are read

Colour, coating, texture, moisture and surface marks — described in a fixed vocabulary, with a confidence value and a record of exactly which image produced it.

Provenance

Every reading can be traced back.

Each result carries the hash of the image that produced it, the engine version, and a run identifier. If a reading looks wrong, it can be reproduced and examined rather than argued about.

Reading
72
+3 vs your baseline
CoatingTHIN
Body colourPINK
MoistureNEUTRAL
Capture qualityHIGH
ComparableYES
Held in your vault. Not a diagnosis. Illustration of the output format.
02 — Calibration

Two ways to get a reference.

To say something changed, you need something to compare against. There are two honest ways to get one, and you don't need to buy anything for either.

ReferenceWhat it gives youWhat it needs
Shade guide in frame A manufactured colour standard with known values lets us solve for the lighting instead of estimating it — so readings hold up across different rooms and different cameras. A shade tab your dental office already owns.
Your own baseline Three to seven captures teach the instrument how much your readings naturally wobble. Anything that exceeds that wobble is a real move, not noise. Nothing. Just the first week.

The second is not a lesser version of the first. It fully answers the question most people actually have — is this changing? The first answers an additional question about comparing across people, which most people don't need.

Your baseline keeps moving with you. Seasons change, phones change, lighting changes — so it's a rolling window, and a poor capture is never allowed to enter it.

03 — The rule that matters

When conditions shift, we show you nothing.

An instrument that always produces a number is indistinguishable from one producing noise, and you'd have no way to tell which you were holding. So when two captures aren't genuinely comparable, we don't estimate. We say so, and we tell you how to fix it.

No reading
Too different from your baseline to compare.
This one was much darker and warmer than your usual captures. Try near a window, facing the light, around the time of day you normally scan.
Comparability: NOT_COMPARABLE · large exposure shift, large white-balance shift
  • Comparable — you get the change, and the baseline it was measured against.
  • Mixed — you get direction only, clearly flagged. No number.
  • Not comparable — you get no reading at all, and specific guidance on the retake.

Refusing to show a number is what makes the numbers we do show worth anything.

04 — Stated plainly

What this instrument cannot do.

Every limit below is real and none of them are scheduled to disappear quietly. If that changes, this page changes with it.

It does not detect or diagnose anything

  • It reads the visible surface of a tongue. That is all it observes.
  • It is not a screening tool and does not decide whether you should be worried.
  • It is not a substitute for a qualified professional, and never will be.

Its numbers are consistent, not yet validated

  • The readings are reproducible: the same image gives the same result, every time.
  • They have not been calibrated against an external reference standard.
  • Consistency and accuracy are different properties. We only claim the first.

Colour is relative without a reference in frame

  • Without a shade guide, readings are meaningful against your own baseline only.
  • Comparisons between two different people need a shared reference target.

Traditional-practice patterns are not live

  • Pattern interpretation requires authorship by licensed practitioners.
  • That work is not finished, so the feature is not switched on.
  • When it ships, it will show supporting evidence, not conclusions.
05 — Access

Early access, honestly described.

This is an instrument under active development. We are not selling lifetime passes or counting down spots. If you want to use it early and tell us where it fails, we would like to hear from you.

Practices interested in the shade-guide workflow: that path is being built with the people who would use it. Same address.