Point the camera. Get an answer.
Send a photo from your app and get back what it shows — a title, a description and structured details you define. Identity, subscription status and usage limits are checked on the way; your app only shows the result.
- Country
- Great Britain
- Condition
- Used · fine
- Confidence
- 0.94
Collectibles and valuables
Stamps, coins, cards, antiques — the pattern behind Stamp Identifier. Name, era and details from one photo.
Plants, animals, food
Species, breed or dish, with the attributes your app cares about — care notes, calories, origin.
Products and labels
Recognise an item or read a label and return the fields your screen needs to fill in.
One photo. A structured answer.
- 1Upload the photo with the user token.Optionally tell Backapp what domain to identify in — stamps, plants, products — and which fields to return. No provider key in the app.
- 2Backapp checks the user and runs the job.Identity, subscription status and usage limit are verified first; declined requests never reach the provider.
- 3Read the result from the job.Poll the job until
completed, then show the title, description and details on your screen.
// CONTENT PENDING: replace with the verified example
const form = new FormData();
form.append('image', { uri, name: 'photo.jpg', type: 'image/jpeg' });
form.append('domain', 'stamps');
form.append('fields', 'country,year,condition');
const res = await fetch(`${BACKAPP_API_URL}/ai/identifications`, {
method: 'POST',
headers: { Authorization: `Bearer ${userToken}` },
body: form,
});
const job = await res.json();
const result = await waitForJob(job.id);
showResult(result.title, result.description, result.fields);{
"id": "job_01HZZ…",
"status": "completed",
"workflow": "image_identification",
"result": {
"title": "Penny Black, 1840",
"description": "World's first adhesive postage stamp…",
"confidence": 0.94,
"fields": {
"country": "Great Britain",
"year": "1840",
"condition": "used, fine"
}
}
}What comes back.
A job with a readable answer and structured fields — ready for a result screen, not a raw caption.
title- Short name of what was identified.
description- One or two readable sentences about it.
confidence- 0–1 score for the match.
fields- The structured attributes you asked for.
status- queued, processing, completed or failed.
Title, description and your own fields
A human-readable identification plus the attributes you ask for, with a confidence score. Supported image formats and size limits are in the docs.
Multiple candidates and value estimates
Ranked alternative matches and domain-specific extras such as market value ranges are being scoped and will be listed here when confirmed.
The identification behind our own collector app.
This workflow is the one Stamp Identifier runs on. Same API, same limits, same subscription check.
Questions about identification?
Can I limit identification to my domain?
Yes. Pass a domain such as stamps, plants or products and the fields you want back. Results are shaped for your screen rather than a generic caption.
What if the photo can’t be identified?
The job completes with a low confidence score and the closest match, so your app can ask for a clearer photo instead of showing a wrong answer.
Which image formats are accepted?
JPEG, PNG and HEIC from the camera roll. Size limits are in the docs.
Does a declined request count against the limit?
No. Identity, subscription and limit checks happen before the job is created. Only accepted jobs count.
Who pays for the AI provider?
Either you, with your own provider key in your Backapp project, or Backapp, billed on usage. Both options are described on the main page.
Add image identification to your app.
Identity, subscriptions and AI workflows from one backend.