Identity documents in digital workflows
Every regulated business — banks, insurance companies, property lettings agents, healthcare providers — requires identity verification. Customers upload a photo of their passport or driving licence, and someone on the back end has to manually key the details into the system.
This creates a bottleneck that slows onboarding, frustrates customers who expect instant decisions, and costs significant staff time at scale. A staffing agency onboarding 200 contractors a month spends around 50 hours just entering ID data.
DocPeel extracts all structured fields from an uploaded ID document in under two seconds, eliminating the manual step entirely.
Document types supported
DocPeel supports passports (all ICAO-compliant formats), national identity cards (European, Middle Eastern, Asian, and Latin American formats), driving licences (UK, US, EU, Australian), and residence permits.
Both the visual inspection zone (VIZ) — the human-readable printed fields — and the machine-readable zone (MRZ) at the bottom of the document are extracted and cross-referenced. Where the MRZ data and VIZ data differ, both are returned with a flag, allowing downstream verification logic to handle the discrepancy appropriately.
Security and compliance considerations
Identity documents are personally identifiable information (PII) subject to GDPR, CCPA, and similar regulations. DocPeel processes each document in an isolated sandbox and discards the source file immediately after extraction unless you explicitly enable document storage.
Extracted data is never used for model training. The API supports field-level masking — for example, you can receive name and expiry date without receiving the document number — to implement data minimisation at the extraction layer.
DocPeel is not an identity verification or fraud detection service. It extracts and structures the data on the document. Liveness checks, database cross-referencing, and fraud scoring are provided by specialist KYC vendors and should be layered on top of the extraction step.
Integrating ID extraction into onboarding flows
The most common pattern is a file upload in an onboarding form that calls the DocPeel API, receives the extracted fields, and pre-fills the remaining form fields for the user to confirm. This eliminates typing errors, speeds up completion, and improves data quality in the CRM or core system.
Alternatively, a back-office workflow can batch-process uploaded ID documents overnight and update customer records without a synchronous API call in the user flow.