Enhanced biologically inspired model

Huang, Y; Huang, K; Wang, L; Tao, D; Tan, T; Li, X

Enhanced biologically inspired model

Huang, Y Huang, K Wang, L Tao, D

Tan, T Li, X

Permalink

Publication Type:: Conference Proceeding
Citation:: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2008
Issue Date:: 2008-09-23

Closed Access

	Filename	Description	Size
	2011001286OK.pdf		910.45 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	Huang, Y	en_US
dc.contributor.author	Huang, K	en_US
dc.contributor.author	Wang, L	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Tan, T	en_US
dc.contributor.author	Li, X	en_US
dc.date.issued	2008-09-23	en_US
dc.identifier.citation	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2008	en_US
dc.identifier.isbn	9781424422432	en_US
dc.identifier.uri	http://hdl.handle.net/10453/17293
dc.description.abstract	It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feed-forward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 x 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications. ©2008 IEEE.	en_US
dc.relation.ispartof	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR	en_US
dc.relation.isbasedon	10.1109/CVPR.2008.4587599	en_US
dc.title	Enhanced biologically inspired model	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
dc.location.activity	Anchorage, AK	en_US
dc.location.activity	Bellevue,Washington, USA
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.publication-status	Published	en_US

Abstract:

It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feed-forward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 x 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications. ©2008 IEEE.

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

http://hdl.handle.net/10453/17293