Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/19915
Title: Scene analysis using an integrated composite neural oscillatory elastic graph matching model
Authors: Lee, RST
Liu, JNK
Keywords: Composite neural oscillatory model
Elastic graph dynamic link model
Gabor filters
Object recognition
Scene analysis
Issue Date: 2002
Publisher: Elsevier
Source: Pattern recognition, 2002, v. 35, no. 9, p. 1835-1846 How to cite?
Journal: Pattern recognition 
Abstract: Scene analysis is so far one of the most important topics in machine vision. In this paper, we present a neural oscillatory model integrated with an elastic graph dynamic link model to provide an automatic means of processing color images. The system involves: (1) multi-frequency bands feature extraction scheme using Gabor filters, (2) automatic figures-ground object segmentation using a composite neural oscillatory model, and (3) object matching using an elastic graph dynamic link model. Using an image gallery of over 3000 color objects, with the recognition of 6000 different scenes, our model shows an average recognition rate of over 95%. For occluded objects in cluttered scenes, the model can still maintain a promising recognition rate of over 87%. Compared with that of the contemporary scene analysis models of gray-level images based on a coupled oscillatory network, the proposed model provides an efficient solution for color images using the composite neural oscillatory model (CNOM). Coupled with the elastic graph dynamic link model (EGDLM), the object recognition process takes less than 35 s on average to complete, which is quite promising in many applications.
URI: http://hdl.handle.net/10397/19915
ISSN: 0031-3203
EISSN: 1873-5142
DOI: 10.1016/S0031-3203(01)00151-0
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

3
Last Week
0
Last month
0
Citations as of Nov 7, 2017

WEB OF SCIENCETM
Citations

2
Last Week
0
Last month
0
Citations as of Nov 15, 2017

Page view(s)

34
Last Week
1
Last month
Checked on Nov 12, 2017

Google ScholarTM

Check

Altmetric



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