Model description:

Face Anti-Spoofing feature enables to prevent false facial verification by using a photo, video or a different substitute for an authorized person’s face. This model can defend against video attacks which is a sophisticated way to trick the face recognition systems, usually requiring a looped video of a victim’s face.

​

Business case:

This model can be used for client authentication.

It can be an ideal complement to facial recognition systems. 

 

Number of classes: 2 (spoof; real)

 

Metrics: 
mAP (mean average precision) tested on 102208 image:
detections_count = 140686, unique_truth_count = 102208
class_id = 0, name = Spoof, ap = 99.33%          (TP = 50513, FP = 3359)
class_id = 1, name = Real, ap = 99.41%           (TP = 49900, FP = 981)
for conf_thresh = 0.25, precision = 0.96, recall = 0.98, F1-score = 0.97
for conf_thresh = 0.25, TP = 100413, FP = 4340, FN = 1795, average IoU = 85.73 %
IoU threshold = 50 %, used Area-Under-Curve for each unique Recall
mean average precision (mAP@0.50) = 0.993667, or 99.37 %

​

System requirements:

Inference time using CPU: 55 ms (on HP Laptop 15-DA0042NH (Processor: Intel(R) Core(TM) i7-8550U CPU))