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. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/TPAMI.2008.48 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
face,vectors,gaussian noise,factor analysis,noise measurement,linear transformation,generative model,gesture recognition,lighting,algorithms,biometry,psychology,system testing,feature vector,computer vision,artificial intelligence,facial expression,pervasive computing,applications,feature extraction,face recognition,em algorithm,pattern recognition,distance metric | Facial recognition system,Computer vision,Feature vector,Pattern recognition,Computer science,Metric (mathematics),Gesture recognition,Feature extraction,Artificial intelligence,Probabilistic logic,Gaussian noise,Generative model | Journal |
Volume | Issue | ISSN |
30 | 6 | 0162-8828 |
Citations | PageRank | References |
65 | 2.23 | 34 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simon Prince | 1 | 914 | 60.61 |
James. H. Elder | 2 | 1136 | 92.03 |
Jonathan Warrell | 3 | 494 | 18.95 |
Fatima M. Felisberti | 4 | 65 | 2.23 |