Visage Technologies
Face Tracking & Analysis

Face detection

Face detection uses powerful techniques to find faces and facial features in still images in form of a well-documented C++ Software Development Kit.

Face detection

Face detection identifies the facial features in facial images containing one or more human faces. Standard image formats are supported for input images. For each detected face it returns the 2D and 3D head pose, 2D and 3D coordinates of facial feature points (chin tip, nose tip, lip corners etc.), and a wealth of other information.


Main features

  • Detects multiple faces and facial features in input images
  • The results are, for each detected face, the 3D head pose, the coordinates of facial feature points, e.g. chin tip, nose tip, lip corners, 3D face model fitted to the face, and a wealth of other information
  • Fully automatic operation
  • Lightweight technology enables high performance across the whole range of supported platforms

Face detection inputs

  • Detection is invariant to the input image format thanks to the raw image interface
  • Detects in color or grayscale images, including near-infrared (internal preprocessing is applied on multichannel images)
  • Detects multiple faces in the input image
  • Configurable face search range (minimal and maximal face size to be detected, relative to image size)
  • Detects faces as small as 30×30 pixels
  • Wide head-pose range: achievable detection on faces with up to 90 degrees of yaw, 30 degrees of roll and 30 degrees of pitch

Face detection outputs

  • 2D and 3D head pose (translation and rotation)
  • Facial feature coordinates in global 3D space, relative to the head or in 2D image space. The feature points are specified according to the MPEG-4 FBA standard.
  • 3D gaze direction (gaze vector)
  • Eye closure
  • 3D model of the face in current pose and expression, returned as single textured 3D triangle mesh; this enables applications such as correct occlusion of virtual objects by the head in AR applications; cutting out the face from the image; drawing the 3D model from a different perspective than the one in the actual image or inserting the face into another video or 3D scene

Application development/platform availability

Go to top