Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/22490
Title: Enhanced biologically inspired model
Authors: Huang, Y
Huang, K
Wang, L
Tao, D
Tan, T
Li, X
Keywords: Feedback
Image recognition
Object detection
Object recognition
Visual databases
Issue Date: 2008
Publisher: IEEE
Source: IEEE Conference on Computer Vision and Pattern Recognition, 2008 : CVPR 2008, 23-28 June 2008, Anchorage, AK, p. 1-8 How to cite?
Journal: IEEE Conference on Computer Vision and Pattern Recognition, 2008 : CVPR 2008, 23-28 June 2008, Anchorage, AK 
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 times 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications.
URI: http://hdl.handle.net/10397/22490
ISBN: 978-1-4244-2242-5
978-1-4244-2243-2 (E-ISBN)
ISSN: 1063-6919
DOI: 10.1109/CVPR.2008.4587599
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Citations as of Feb 12, 2016

Page view(s)

50
Last Week
0
Last month
Checked on May 28, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.