What it does
Skin Ledger measures skin change against your own baseline instead of an average face. You scan a photo, the YouCam Skin API scores eight concerns, and the app keeps a dated record. Four scans later you can see which concerns actually moved — which is the question people really ask ("did the azelaic acid do anything?").
It also reads product labels: point the camera at an ingredient list and the app extracts the actives and attaches them to your change log. A copilot then answers "why did acne improve?" using only the numbers in your own record, and says "not enough data" when there isn't any.
How it's built
A zero-dependency Node server proxies the YouCam API so the key never reaches the browser. Records stay in localStorage — no account, no cloud. The label pipeline is OCR.space for text plus a local ingredient parser (102 INCI names with Levenshtein repair), so the critical path never waits on a model.
What makes it different
Most skin apps show a score. This one shows a delta with dates, and refuses to explain a change it cannot see in the record. The HD path (15 scores + 24 region readings) is one toggle away, behind an up-front pixel check so you never spend API units on a face that is too small.
What's next
Weekly reminders, a shareable one-page report, and a proper diff view for two scans side by side.
Built With
- canvas
- html5
- javascript
- node.js
- youcam-api
Log in or sign up for Devpost to join the conversation.