Example-Based Learning for View-Based Human Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Using Temporal Image Sequence
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Beyond Eigenfaces: Probabilistic Matching for Face Recognition
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Face Recognition Based on Fitting a 3D Morphable Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic recognition of human faces from video
Computer Vision and Image Understanding - Special issue on Face recognition
Learning over sets using kernel principal angles
The Journal of Machine Learning Research
Robust Real-Time Face Detection
International Journal of Computer Vision
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 5 - Volume 05
Boosted manifold principal angles for image set-based recognition
Pattern Recognition
Classification of face images using local iterated function systems
Machine Vision and Applications
Shape classification by manifold learning in multiple observation spaces
Information Sciences: an International Journal
Hi-index | 0.00 |
In this work, we consider face recognition from face motion manifolds (FMMs). The use of the resistor-average distance (RAD) as a dissimilarity measure between densities confined to FMMs is motivated in the proposed information-theoretic approach to modelling face appearance. We introduce a kernel-based algorithm that makes use of the simplicity of the closed-form expression for RAD between two Gaussian densities, while allowing for modelling of complex and nonlinear, but intrinsically low-dimensional manifolds. Additionally, it is shown how geodesically local FMM structure can be modelled, naturally leading to a stochastic algorithm for generalizing to unseen modes of data variation. Recognition performance of our method is demonstrated experimentally and is shown to exceed that of state-of-the-art algorithms. Recognition rate of 98% was achieved on a database of 100 people under varying illumination.