2005 | OriginalPaper | Buchkapitel
On Dimensionality Reduction for Client Specific Discriminant Analysis with Application to Face Verification
verfasst von : Xiaojun Wu, Kittler Josef, Jingyu Yang, Messer Kieron, Shitong Wang, Jieping Lu
Erschienen in: Advances in Biometric Person Authentication
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this paper we propose a study on dimensionality reduction for client specific discriminant analysis with application to face verification. A new algorithm of face verification based on client specific discriminant analysis is developed. Two aspects of improvement are made in the new algorithm. First, a dimensionality reduction based on the between-class scatter matrix is introduced which is more efficient than that based on the population scatter matrix. The second improvement lies in the use of a new Fisher criterion function which is introduced in order to reduce the computational complexity of the client specific discriminant analysis problem. The experimental results obtained on the internationally recognized facial database XM2VTS using the Lausanne protocol show the effectiveness of the proposed method.