Visio-lization: generating novel facial images
ACM SIGGRAPH 2009 papers
Face recognition across pose: A review
Pattern Recognition
Pose-Invariant Face Matching Using MRF Energy Minimization Framework
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Efficient statistical face recognition across pose using local binary patterns and Gabor wavelets
BTAS'09 Proceedings of the 3rd IEEE international conference on Biometrics: Theory, applications and systems
Probabilistic learning for fully automatic face recognition across pose
Image and Vision Computing
Fovea intensity comparison code for person identification and verification
Engineering Applications of Artificial Intelligence
An effective approach to pose invariant 3D face recognition
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part I
Computer Vision and Image Understanding
Regression based automatic face annotation for deformable model building
Pattern Recognition
Cross-pose face recognition based on partial least squares
Pattern Recognition Letters
Class dependent factor analysis and its application to face recognition
Pattern Recognition
Remote identification of faces: Problems, prospects, and progress
Pattern Recognition Letters
Robust pose invariant face recognition using coupled latent space discriminant analysis
Computer Vision and Image Understanding
Morphable displacement field based image matching for face recognition across pose
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Parametric manifold of an object under different viewing directions
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Pose-robust face recognition via sparse representation
Pattern Recognition
Regularized latent least square regression for cross pose face recognition
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Compensating for speaker or lexical variabilities in speech for emotion recognition
Speech Communication
Hi-index | 0.14 |
Face recognition algorithms perform very unreliably when the pose of the probe face is different from the gallery face: typical feature vectors vary more with pose than with identity. We propose a generative model that creates a one-to-many mapping from an idealized "identity" space to the observed data space. In identity space, the representation for each individual does not vary with pose. We model the measured feature vector as being generated by a pose-contingent linear transformation of the identity variable in the presence of Gaussian noise. We term this model "tied" factor analysis. The choice of linear transformation (factors) depends on the pose, but the loadings are constant (tied) for a given individual. We use the EM algorithm to estimate the linear transformations and the noise parameters from training data. We propose a probabilistic distance metric which allows a full posterior over possible matches to be established. We introduce a novel feature extraction process and investigate recognition performance using the FERET, XM2VTS and PIE databases. Recognition performance compares favourably to contemporary approaches.