Photo-verified authenticity

Prove the physical object, not just the certificate.

A valid QR proves the certificate is real. Visual authentication proves the object in the buyer's hands is the one that was certified. Consumers photograph the product on /verify and Fidaty matches it against the producer's reference images with CLIP embeddings — a second, independent layer of trust.

CLIP 512-dim visual embeddingsCosine match on pgvectorLive capture on mobileThe photo is never stored

2 layers

Of trust

Certificate + object

512-dim

CLIP embedding

Per reference view

0

Photos stored

Embedded then discarded

Tier-driven

Match thresholds

Tunable, no redeploy

Why visual authentication

The QR can be copied. The object is harder to fake.

Counterfeiters clone QR codes and links. Visual authentication closes that gap: it ties the digital certificate to the visual identity of the physical product, so a cloned code on a fake item fails the photo match.

ENROLL

Reference photos, embedded at the source.

The producer uploads one or more reference views (front, back, serial detail) for a certificate. Each is embedded with a CLIP-class vision model and stored as a 512-dim vector — never as a raw image a verifier can lift.

Multi-view enrollment

Front, back and serial-detail views make the fingerprint robust and far harder to spoof with a single photo pulled from the web.

CLIP 512-dim embeddings

A vision model turns each reference into a 512-dimensional vector on pgvector. Pluggable provider (HuggingFace / custom) with clean degradation.

Producer-scoped storage

Reference images live in a dedicated bucket, write-restricted to the certificate's owner via row-level security.

MATCH

The consumer photographs the object.

On /verify, the consumer takes a live photo. Fidaty embeds it server-side and compares it to the certificate's reference views with cosine similarity — returning a confidence band, never a raw yes/no.

Live capture, downscaled client-side

On mobile the camera opens directly; the image is downscaled before upload for speed and privacy.

Cosine similarity on pgvector

The live embedding is matched against the certificate's reference vectors. The best score drives the verdict.

The photo is never stored

The submitted image is embedded and discarded. Only the verdict, score and coarse geolocation are kept.

TRUST

A confidence band, not a false verdict.

Visual authentication returns strong / weak / no match — deliberately a confidence band, because a binary 'fake' carries legal weight the platform won't own. Failed matches also feed the counterfeit radar.

Strong / weak / no match

Tier-driven thresholds map cosine similarity to a clear, honest confidence band shown next to the on-chain proof.

Feeds counterfeit detection

Every geolocated no-match becomes a signal for the cross-signal counterfeit cluster radar.

Degrades cleanly

Without a configured vision provider the feature simply hides — no broken UI, no false confidence.

Use cases

Real scenarios where this service delivers.

Luxury & collectibles

A buyer on the secondary market photographs a watch or handbag and confirms it matches the brand's reference images before paying.

Spare parts & safety

An installer checks that a safety-critical component visually matches the certified part, not a look-alike.

Art & editions

A gallery confirms the physical piece matches the artist's enrolled references, beyond the certificate alone.

Pharma & cosmetics

Packaging is matched visually to catch refilled or repackaged counterfeits that clone the QR.

Why Fidaty

Built for brands that take trust seriously.

Every service in the Fidaty platform is integrated with the rest: identity, compliance, analytics and consumer engagement flow seamlessly. No data silos, no duplicate work.

Book a demo
  • Authenticates the physical object, not only the digital certificate
  • The consumer photo is never stored — embedded then discarded
  • Multi-view enrollment resists single-photo spoofing
  • Match thresholds are tier-driven and tunable without redeploy
  • Failed matches power the counterfeit cluster radar
  • Degrades cleanly when no vision provider is configured
Verified on-chain

Add a visual layer to your authentication.

Enroll reference photos per certificate and let consumers confirm the physical object on /verify.