Face de-identification
Parameterized kernel principal component analysis: Theory and applications to supervised and unsupervised image alignment
Semi-supervised learning of multi-factor models for face de-identification
Filtered component analysis to increase robustness to local minima in appearance models
Learning kernel expansions for image classification
Temporal segmentation of facial behavior
Model-based face de-identification
Research Forensic Library
We invite you to also search the Research Forensic Library, a curated collection of publicly-accessible material relating to every discipline of the forensic sciences.