Verification (1:1)
Verification answers "is this the claimed person?" — the complete process of recognising a person from a live capture by comparing the probe against one stored identity selected by a presented claim (badge, card, PIN, account).
How it works
Verification is a full pipeline, not a single call:
Matching operates on templates — compact binary representations of the biometric sample (for scale: a face template in the SFE Toolkit is 522 bytes) — so the application stores templates rather than images.
Liveness is the security check. Where the use case calls for it, passive liveness typically runs before template extraction and matching: if a probe fails liveness, abort and don't match a spoofed input. Depending on the integration it can also run after matching. See Liveness.
Modalities
The same feature is implemented by several SDKs, each covering different modalities. Pick by the modality you need and where matching runs:
| SDK | Runs | Face | Iris | Palm | Fingerprint |
|---|---|---|---|---|---|
| SFE Toolkit | On-device | ✓ | ✓ | ✓ | — |
| IDKit | On-device | — | — | — | ✓ |
| Enrollment SDK | Desktop / server / Android | ✓ | ✓ | — | ✓ |
| ANSI/ISO SDK | On-device / server | — | — | — | ✓ |
Notes:
- SFE Toolkit face, palm and iris templates are 522 bytes.
- Proprietary fingerprint template size is ~2KB.
- Enrollment SDK covers face, iris and fingerprint (no palm).
- ANSI/ISO SDK is fingerprint-only and uses standard templates — ANSI ≤ 1568 bytes, ISO ≤ 1566 bytes.
SFE Toolkit implementation
On the SFE Toolkit (face, palm, iris), each pipeline step maps to a capability — follow a link for the per-capability detail:
| Pipeline step | Face | Palm | Iris |
|---|---|---|---|
| Detection | Face Detection | Palm detection | Iris detection |
| Landmarks / keypoints | Face Landmarks | Palm landmarks | — |
| Quality / attributes | Face Quality | Palm Attributes | — |
| Template extraction | Face Template Extraction | Palm Template Extraction | Iris Template Extraction |
| 1:1 verification | Face Verification | Palm Verification | Iris Verification |
Passive liveness is a separate feature — see Liveness.
IDKit implementation
IDKit covers the fingerprint modality. Its pipeline steps map to:
| Pipeline step | IDKit capability |
|---|---|
| Quality / presence | Fingerprint quality and presence |
| Template extraction | Template extraction |
| 1:1 verification | Verification (one-to-one) |
Fingerprint capture and enrollment are handled by the Enrollment SDK.
ANSI/ISO SDK implementation
The ANSI/ISO SDK covers fingerprint with standards-based templates (1:1 only):
| Pipeline step | ANSI/ISO SDK capability |
|---|---|
| Template extraction (generator) | Capabilities |
| Quality | Fingerprint quality |
| 1:1 verification (matcher) | Similarity scores |
Enrollment SDK implementation
On the Enrollment SDK (face, iris, fingerprint), each pipeline step maps to a function:
| Pipeline step | Face | Iris | Fingerprint |
|---|---|---|---|
| Detection | FaceDetector::Detect | IrisDetector::Detect | PrintExecutor::AlgoSegment / NeuralSegment |
| Landmarks / keypoints | FaceExecutor::GetKeypoint | — | — |
| Quality / attributes | OFIQFace | IrisExecutor::IrisQuality | PrintExecutor::CalculateNFIQ2 |
| Template extraction | Applicant::AddFace | Applicant::AddIris | ICSExtractor::Extract · Applicant::AddPrint |
| 1:1 verification | ModalitiesVerifyMatcher::MatchFaces | ModalitiesVerifyMatcher::MatchIrises | ModalitiesVerifyMatcher::MatchPrints |
Full signatures: API Reference.
Key considerations
- Gate on quality before liveness and extraction. Reject low-quality captures early, and check the extracted template (not just the image) — an acceptable image can still yield a weak template.
- Tune the threshold to your FMR/FNMR target on representative data; vendor/example values are illustrative, not production security settings.
- 1:1 can be tuned differently from 1:N — verification often tolerates a lighter extraction mode and a lower threshold than a large 1:N search; tune per use case.
- Keep the extraction algorithm/version consistent between the stored template and the probe; templates are only comparable within one algorithm family.
- Validate on the platform and data you deploy — quantized edge models don't reproduce desktop/server float results exactly; revalidate FAR/FRR and liveness operating points per target.
Related pages
- Identification (1:N) (the sibling workflow — search the whole gallery)
- Enrollment (creates the stored identity this feature compares against)
- Liveness (face & palm)