Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/8239
Title: Neural computation approach for developing a 3D shape reconstruction model
Authors: Cho, SY
Chow, TW
Keywords: Computer vision
Feedforward neural nets
Image reconstruction
Learning (artificial intelligence)
Radial basis function networks
Reflectivity
Stereo image processing
Issue Date: 2001
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on neural networks, 2001, v. 12, no. 5, p. 1204-1214 How to cite?
Journal: IEEE transactions on neural networks 
Abstract: The shape from shading problem refers to the well-known fact that most real images usually contain specular components and are affected by unknown reflectivity. In this paper, these limitations are addressed and a new neural-based 3D shape reconstruction model is proposed. The idea behind this approach is to optimize a proper reflectance model by learning the parameters of the proposed neural reflectance model. In order to do this, new neural-based reflectance models are presented. The feedforward neural network (FNN) model is able to generalize the diffuse term, while the RBF model is able to generalize the specular term. A hybrid structure of FNN-based and RBF-based models is also presented because most real surfaces are usually neither Lambertian models nor ideally specular models. Experimental results, including synthetic and real images, are presented to demonstrate the performance of our approach given different specular effects, unknown illuminate conditions, and different noise environments
URI: http://hdl.handle.net/10397/8239
ISSN: 1045-9227
DOI: 10.1109/72.950148
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

22
Citations as of Apr 30, 2016

WEB OF SCIENCETM
Citations

18
Last Week
0
Last month
0
Citations as of Aug 15, 2017

Page view(s)

34
Last Week
5
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



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