Issue loans to the real customer, not to someone with another person’s passport
The customer shows a document and takes one selfie — no camera commands. Biometric.Vision verifies identity at the counter or in the app so a mismatch is visible before money is issued, and an honest customer does not stall in a queue because of a manual check.
Tighten the check — without stopping the queue
At the counter the cashier needs to see quickly who is standing there. Someone else’s or a forged passport, a stand-in customer — a mistake turns into a dispute with the item’s owner and police attention. In the app and Webview those risks add deepfakes and substituted video.
But turning every loan into a long manual review is not an option either. While staff eyeball the face and ask the customer to repeat camera motions, the queue grows. An honest customer may simply walk to the pawnshop next door.
risk
risk
review
issueFrom document to verdict — in one counter flow
One standard for a loan, a return visit and a redeem: document, liveness and face in one scenario. The queue keeps moving, someone else’s identity is not a pass to a loan, and a returning customer has an easier path back.
Document
The customer shows a passport or another supported document.
Recognition
The system extracts the data and checks the document.
One selfie
Passive liveness and face match run as one action.
SelfieDocumentVerdict
The result returns to the staff UI before the loan is issued. If the check fails, staff follow the pawnshop’s rules.
One selfie instead of commands in front of the camera
Passive liveness works from one selfie — no ask to turn the head, blink or smile. For an honest customer it is a normal loan step. For an attempt to show a screen, a mask or substituted video it is a separate spoofing check.
Passive liveness is certified to ISO 30107-3 Level 2.
Someone else’s document will not become grounds for a loan
The system reads the document, checks liveness and matches the customer’s face to the photo. In the verdict staff see separate statuses for document, liveness and face match — so someone else’s passport, a stand-in or a deepfake is caught before the pledge is booked.
Match accuracy is 99.9997%. The algorithm is independently tested in NIST FRVT.
CustomerDocumentThe customer comes back for the pledge — you recognize them by face
The pledge goes back to the person who left it: on a return visit staff confirm identity by face instead of another manual check of the document and contract. A returning customer does not redo the full document path, and the pawnshop has fewer redeem disputes.
After the first full check the biometric profile can be reused. The pawnshop decides where to keep a full check and where to allow entry or redeem by face.
NowProfileClassic integration
If your team prefers to assemble the architecture itself, connect ready SDKs and APIs.
Web SDK / Flow Widget
A ready JS camera component for web registration or an in-app Webview. The check runs inside your onboarding; the design follows your brand book.
Mobile SDK
A native verification flow in the mobile app: camera access and biometric micropacket transfer even on a weak connection.
REST API
Layer results and the final verdict arrive in your backend logic: risk rules and the decision stay on your side. Auth via X-API-KEY.
MCP server for AI agents
Connect checks to agent scenarios without writing glue code. Works with Claude, GPT and any MCP client.
Questions and answers
Issue loans to customers, not to people with someone else’s documents
Connect document, liveness and face checks to the counter, the app or your internal system. Keep the familiar path for an honest customer and add an objective verdict before money is issued.
Numbers and facts
- 433+
- Document types —Support for passports and hundreds of other document types worldwide
- 180+
- Supported countries —Global coverage for checks across jurisdictions
- 40 sec
- Onboarding time —User registration and verification in under a minute
- 99%
- Technology accuracy —High-accuracy AI document recognition and verification