University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Learning a representation with the block-diagonal structure for pattern classification.

He-Feng, Yin, Xiao-Jun, Wu, Kittler, Josef and Zhen-Hua, Feng (2019) Learning a representation with the block-diagonal structure for pattern classification. PATTERN ANALYSIS AND APPLICATIONS.

[img] Text
PAA_Manuscript.pdf - Accepted version Manuscript
Restricted to Repository staff only until 13 December 2020.

Download (417kB)


Sparse-representation-based classification (SRC) has been widely studied and developed for various practical signal classification applications. However, the performance of a SRC-based method is degraded when both the training and test data are corrupted. To counteract this problem, we propose an approach that learns representation with block-diagonal structure (RBDS) for robust image recognition. To be more specific, we first introduce a regularization term that captures the block-diagonal structure of the target representation matrix of the training data. The resulting problem is then solved by an optimizer. Last, based on the learned representation, a simple yet effective linear classifier is used for the classification task. The experimental results obtained on several benchmarking datasets demonstrate the efficacy of the proposed RBDS method. The source code of our proposed RBDS is accessible at

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
He-Feng, Yin
Xiao-Jun, Wu
Zhen-Hua, Feng
Date : 12 December 2019
Funders : EPSRC
DOI : 10.1007/s10044-019-00858-4
Grant Title : U.K. Ministry of Defence
Copyright Disclaimer : Copyright © 2019, Springer Nature
Uncontrolled Keywords : Pattern classifcation · Low-rank and sparse representation · Block-diagonal structure
Depositing User : James Marshall
Date Deposited : 23 Jan 2020 11:49
Last Modified : 18 Feb 2020 10:01

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800