AI Models¶
This SDK makes extensive use of AI models, particularly for minutiae detection and encoding tasks.
The following models are available:
Model |
Size |
Description |
|---|---|---|
FingerAligner1A |
2009 kB |
Aligns a fingerprint before encoding. |
FingerDetector2A |
2855 kB |
Detects one or multiple fingerprints in images. |
FingerEncoder1A |
4,683 kB |
Provides proprietary information at the fingerprint level to increase match accuracy. |
FingerMinutiaDetector3B |
3,522 kB |
Detects minutiae. Corresponds to id3_13B1 submission to NIST MINEX III. |
FingerMinutiaEncoder1A |
1,697 kB |
Provides proprietary information at the minutiae level to increase match accuracy. |
Important
AI model files¶
AI model files have the .id3nn extension. You must copy the necessary data files into your application package. If you wish to reduce the size of your application, we recommend copying only the files required by the biometric algorithm.
In your application’s source code you should specify location of these files.
Warning
AI model files MUST NOT be renamed.
Loading AI models¶
It is recommended to load the AI models on application startup. The FingerLibrary Class provides methods for loading and unloading AI model file in memory.
An example is given below:
FingerLibrary.load_model(ai_models_path, FingerModel.FINGER_DETECTOR_2A, ProcessingUnit.CPU)
FingerLibrary.load_model(ai_models_path, FingerModel.FINGER_MINUTIA_DETECTOR_3B, ProcessingUnit.CPU)
FingerLibrary.load_model(ai_models_path, FingerModel.FINGER_ALIGNER_1A, ProcessingUnit.CPU)
FingerLibrary.load_model(ai_models_path, FingerModel.FINGER_ENCODER_1A, ProcessingUnit.CPU)
Processing units¶
The inference of the AI models can be executed on either the CPU or the GPU if available, by specifying a ProcessingUnit Enumeration. The GPU options selects a default backend depending on your platform. Detailed backend options are available to ensure a specific backend.
Warning
Inference on GPU is an experimental feature. Some models might be unstable on some backend or provide nonsense result. We strongly encourage you to verify the results on those backends, and contact our support in case of inadequate behaviour.