Learning structurally discriminant features in 3D faces

In this paper, we derive a data mining framework to analyze 3D features on human faces. The framework leverages kernel density estimators, genetic algorithm and an information complexity criterion to identify discriminant feature-clusters of lower dimensionality. We apply this framework on human face anthropometry data of 32 features collected from each of the 300 3D face mesh models. The feature-subsets that we infer as the output establishes domain knowledge for the challenging problem of 3D face recognition with dense 3D gallery models and sparse or low resolution probes.

• Type: Conference
• Year: 2008
• Where: ICIP
• Authors: Sreenivas R. Sukumar, Hamparsum Bozdogan, David L. Page, Andreas Koschan, Mongi A. Abidi
• Keywords: Data Mining Framework, Dense 3D Gallery, Face Mesh Models, Framework Leverages Kernel, Human Face Anthropometry, ICIP 2008, Image Processing