A Machine-Learning Approach to Keypoint Detection and Landmarking on 3D Meshes
International Journal of Computer Vision
Automatic facial expression recognition in real-time from dynamic sequences of 3D face scans
The Visual Computer: International Journal of Computer Graphics
| Hi-index | 0.00 |
Key points on 3D surfaces are points that can be extracted repeatably over a wide range of 3D imaging conditions. They are used in many 3D shape processing applications, for example, to establish a set of initial correspondences across a pair of surfaces to be matched. Typically, key points are extracted using extremal values of a function over the 3D surface, such as the descriptor map for Gaussian curvature. That approach works well for salient points, such as the nose-tip, but can not be used with other less pronounced local shapes. In this paper, we present an automatic method to detect key points on 3D faces, where these key points are locally similar to a set of previously learnt shapes, constituting a 'local shape dictionary'. The local shapes are learnt at a set of 14 manually-placed landmark positions on the human face. Local shapes are characterised by a set of 10 shape descriptors computed over a range of scales. For each landmark, the proportion of face meshes that have an associated key point detection is used as a performance indicator. Repeatability of the extracted key points is measured across the FRGC v2 database.