Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageUndefined/Unknown
Title of host publicationProceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission
Place of PublicationWashington, DC, USA
PublisherIEEE Computer Society
Number of pages8
Publication statusPublished - 2011

Publication series

Name3DIMPVT '11
PublisherIEEE Computer Society


  • 3D face, keypoint detection, local 3D descriptors

Cite this