Biologically Inspired Tensor Features

Mu, Y; Tao, D; Li, X; Murtagh, F

Biologically Inspired Tensor Features

Mu, Y Tao, D

Li, X Murtagh, F

Permalink

Publication Type:: Journal Article
Citation:: Cognitive Computation, 2009, 1 (4), pp. 327 - 341
Issue Date:: 2009-12-01

Closed Access

	Filename	Description	Size
	2011000270OK.pdf		923.02 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Mu, Y	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Li, X	en_US
dc.contributor.author	Murtagh, F	en_US
dc.date.issued	2009-12-01	en_US
dc.identifier.citation	Cognitive Computation, 2009, 1 (4), pp. 327 - 341	en_US
dc.identifier.issn	1866-9956	en_US
dc.identifier.uri	http://hdl.handle.net/10453/15206
dc.description.abstract	According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of object recognition in the primate's visual cortex. Therefore, it is time to reconsider face recognition by using biologically inspired features. In this paper, we represent face images by utilizing the C1 units, which correspond to complex cells in the visual cortex, and pool over S1 units by using a maximum operation to reserve only the maximum response of each local area of S1 units. The new representation is termed C1 Face. Because C1 Face is naturally a third-order tensor (or a three dimensional array), we propose three-way discriminative locality alignment (TWDLA), an extension of the discriminative locality alignment, which is a top-level discriminate manifold learning-based subspace learning algorithm. TWDLA has the following advantages: (1) it takes third-order tensors as input directly so the structure information can be well preserved; (2) it models the local geometry over every modality of the input tensors so the spatial relations of input tensors within a class can be preserved; (3) it maximizes the margin between a tensor and tensors from other classes over each modality so it performs well for recognition tasks and (4) it has no under sampling problem. Extensive experiments on YALE and FERET datasets show (1) the proposed C1Face representation can better represent face images than raw pixels and (2) TWDLA can duly preserve both the local geometry and the discriminative information over every modality for recognition. © 2009 Springer Science+Business Media, LLC.	en_US
dc.relation.ispartof	Cognitive Computation	en_US
dc.relation.isbasedon	10.1007/s12559-009-9028-5	en_US
dc.title	Biologically Inspired Tensor Features	en_US
dc.type	Journal Article
utslib.citation.volume	4	en_US
utslib.citation.volume	1	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	1109 Neurosciences	en_US
utslib.for	1702 Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	4	en_US
pubs.publication-status	Published	en_US
pubs.volume	1	en_US

Abstract:

According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of object recognition in the primate's visual cortex. Therefore, it is time to reconsider face recognition by using biologically inspired features. In this paper, we represent face images by utilizing the C1 units, which correspond to complex cells in the visual cortex, and pool over S1 units by using a maximum operation to reserve only the maximum response of each local area of S1 units. The new representation is termed C1 Face. Because C1 Face is naturally a third-order tensor (or a three dimensional array), we propose three-way discriminative locality alignment (TWDLA), an extension of the discriminative locality alignment, which is a top-level discriminate manifold learning-based subspace learning algorithm. TWDLA has the following advantages: (1) it takes third-order tensors as input directly so the structure information can be well preserved; (2) it models the local geometry over every modality of the input tensors so the spatial relations of input tensors within a class can be preserved; (3) it maximizes the margin between a tensor and tensors from other classes over each modality so it performs well for recognition tasks and (4) it has no under sampling problem. Extensive experiments on YALE and FERET datasets show (1) the proposed C1Face representation can better represent face images than raw pixels and (2) TWDLA can duly preserve both the local geometry and the discriminative information over every modality for recognition. © 2009 Springer Science+Business Media, LLC.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/15206