Discriminant incoherent component analysis

Georgakis, Christos and Panagakis, Yannis and Pantic, Maja (2016) Discriminant incoherent component analysis. IEEE Transactions on Image Processing, 25 (5). pp. 2021-2034. ISSN 1057-7149

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (19MB) | Preview

Abstract

Face images convey rich information which can be perceived as a superposition of low-complexity components associated with attributes, such as facial identity, expressions, and activation of facial action units (AUs). For instance, low-rank components characterizing neutral facial images are associated with identity, while sparse components capturing non-rigid deformations occurring in certain face regions reveal expressions and AU activations. In this paper, the discriminant incoherent component analysis (DICA) is proposed in order to extract low-complexity components, corresponding to facial attributes, which are mutually incoherent among different classes (e.g., identity, expression, and AU activation) from training data, even in the presence of gross sparse errors. To this end, a suitable optimization problem, involving the minimization of nuclear-and l1 -norm, is solved. Having found an ensemble of class-specific incoherent components by the DICA, an unseen (test) image is expressed as a group-sparse linear combination of these components, where the non-zero coefficients reveal the class(es) of the respective facial attribute(s) that it belongs to. The performance of the DICA is experimentally assessed on both synthetic and real-world data. Emphasis is placed on face analysis tasks, namely, joint face and expression recognition, face recognition under varying percentages of training data corruption, subject-independent expression recognition, and AU detection by conducting experiments on four data sets. The proposed method outperforms all the methods that are compared with all the tasks and experimental settings.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 23765
Notes on copyright: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Useful Links:
Depositing User: Yannis Panagakis
Date Deposited: 06 Mar 2018 16:59
Last Modified: 07 Dec 2018 08:26
URI: http://eprints.mdx.ac.uk/id/eprint/23765

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year