A novel discriminant non-negative matrix factorization algorithm with applications to facial image characterization problems

Kotsia, Irene and Zafeiriou, Stefanos and Pitas, Ioannis (2007) A novel discriminant non-negative matrix factorization algorithm with applications to facial image characterization problems. IEEE Transactions on Information Forensics and Security, 2 (3). pp. 588-595. ISSN 1556-6013

Full text is not in this repository.

This item is available in: Library Catalogue

Abstract

The methods introduced so far regarding discriminant non-negative matrix factorization (DNMF) do not guarantee convergence to a stationary limit point. In order to remedy this limitation, a novel DNMF method is presented that uses projected gradients. The proposed algorithm employs some extra modifications that make the method more suitable for classification tasks. The usefulness of the proposed technique to frontal face verification and facial expression recognition problems is demonstrated.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
A. > School of Science and Technology > Computer Science > Intelligent Environments Research Group
Item ID: 9593
Useful Links:
Depositing User: Devika Mohan
Date Deposited: 26 Nov 2012 07:16
Last Modified: 13 Oct 2016 14:25
URI: http://eprints.mdx.ac.uk/id/eprint/9593

Actions (login required)

Edit Item Edit Item