It is incorrect to state accuracy based simply on true positives vs false positives as these will vary with different image qualities, user-selected thresholds and other factors.
In the example given here, review thresholds have been optimised to maximise identifications. It would be wrong and misleading to conclude an accuracy rate of 33% based on a simplistic ratio of true positives to total positives.
The reality is that the identification success rate is 100% in this example. The false positive rate is very low but could be reduced or eliminated if required by some further fine-tuning.
The quantity of faces presented for review by users is determined by setting and fine-tuning review thresholds and are affected by many environmental variables. To know more about how NeoFace Watch Facial Recognition identifies similar image, click to download the full version of the report.