Face++ detect performance report
According to the FDDB (Face Detection Data Set and Benchmark) report, Face++ delivers state-of-the-art face detection performance among its commercial competitors.
FDDB is a data set of face regions designed for studying the problem of unconstrained face detection. This data set contains the annotations for 5171 faces in a set of 2845 images taken from the Faces in the Wild data set.
In the below diagrams, the horizontal axis represents the number of false positive faces reported by the detector, while the vertical one shows the true positive rate. The closer the curve approaches to the upper-left corner, the better the corresponding detector does on this benchmark.
It can be seen from the discrete score diagram, Face++ holds the best performance 0.8 TPR (True positive rate) with nearly 30 false positives. Notice that, in continuous score situation, Face++ detector enjoys a great performance margin over other detectors.Click here to get more.
Face++ delivers the leading face techs to global developers. It’s our pleasure to have your witness of improvements of Face++. Stay focus!