Tied Factor Analysis for Face Recognition across Large Pose Differences

Citations Over TimeTop 1% of 2008 papers

Abstract

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.

Related Papers

• → Human Pose Co-Estimation and Applications(2012)40 cited
• → A survey on Pose Estimation using Deep Convolutional Neural Networks(2021)6 cited
• → Cascaded Pyramid Network for 3D Human Pose Estimation Challenge(2018)3 cited
• → Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose\n Estimation(2020)
• → LocalPose: Object Pose Estimation with Local Geometry Guidance(2023)