Facial Visual Analysis


Facial detection software use landmarks called nodal points to detect faces. It maps out a face by measering distances between eyes, ears, mouth aswell as the shape of a face. With this information it creates a code a so called face print.


Each human face has approximately 80 nodal points. Some of these measured by the Facial Recognition Technology are:

- Distance between the eyes

- Width of the nose

- Depth of the eye sockets

- The shape of the cheekbones

- The length of the jaw line

3D Face Model

By introducing 3D face shape model, we use procrustes analysis to achieve pose-free facial landmark initialization. Then a two-stage cascaded deformable shape model is applied to effectively and efficiently localize the facial landmarks. Validating the result on not only laboratory face databases but also face-in-the-wild databases, the framework reveals its advantages in handling extreme head pose variation, expression and complex background.
- Experience in the tens of thousands of hours of work on annotation frames
- Accurate labeling by frames