Expand description
Core types for an on-device face liveness and verification engine.
This crate is intentionally UI-agnostic and Flutter-agnostic. It should be usable from Flutter, Tauri, native Rust apps, servers, or any host that can call Rust/WASM.
Structs§
- Bounding
Box - Captured
Photo Analysis - Face
Analysis - Face
Verification Engine - Headless verification engine. It owns the model bundle and thresholds, and is the future home for the ONNX/tract image-analysis pipeline.
- Frame
Analysis - Hand
Analysis - Image
Input - Landmarks
- Liveness
Challenge - A complete liveness challenge.
- Model
Asset - One model file plus the metadata needed to wire it into a pipeline.
- Model
Bundle - A complete, swappable model set.
- Model
Validation - Nsfw
Scores - Point
- Pose
Check - Result of validating one frame or one captured photo against a step.
- Session
Tick Json Result - Verification
Checks - Verification
Result - Verification
Session - Verification
Thresholds - Runtime knobs used by the liveness pipeline.
Enums§
- Challenge
Step - One step in a liveness challenge.
- Face
Verification Error - Public error type for the core.
- Model
Format - Serialized model format accepted by the Rust runtime.
- Model
Role - Role a model plays in the full image-analysis pipeline.
- Session
Decision - Touch
Target - Facial target used by hand-to-face liveness checks.
Constants§
Traits§
Functions§
- analyze_
image_ json - compute_
yaw - face_
distance - generate_
challenge_ json - new_
session_ json - tick_
session_ json - validate_
model_ bundle_ json - validate_
pose - validate_
pose_ json - verify_
captured_ photos - verify_
captured_ photos_ json - verify_
images_ json