Web API including demos, documentation and samples of usage
Service for face and facial features finding and recognition
Your face tells everything
Extract emotional insights from facial emotions
Optical Flow based Tracking
Optical flow is defined as spatio-temporal image brightness variations. To track a face across a sequence of frames, we use Lucas-Kanade optical flow algorithm to estimate the motion of extracted facial features between adjacent frames in the sequence.
CAMShift based Tracking
The CAMShift algorithm is an adaption of the Mean Shift algorithm for object tracking. The Mean Shift algorithm is a robust, non-parametric technique that climbs the gradient of a probability distribution to find the mode (peak) of the distribution.
Main Output of Single Face Tracker
Face detection and tracking is the process of determining whether or not a face is present in an image. Unlike face recognition—which distinguishes different human faces, face detection only indicates whether or not a face is present in an image.