Please use this identifier to cite or link to this item:
Title: Learning parametric specular reflectance model by radial basis function network
Authors: Cho, SY
Chow, TW
Issue Date: 2000
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on neural networks, 2000, v. 11, no. 6, p. 1498-1503 How to cite?
Journal: IEEE transactions on neural networks 
Abstract: For the shape from shading problem, it is known that most real images usually contain specular components and are affected by unknown reflectivity. In the paper, these limitations are addressed and a neural-based specular reflectance model is proposed. The idea of this method is to optimize a proper specular model by learning the parameters of a radial basis function network and to recover the object shape by the variational approach with this resulting model. The obtained results are very encouraging and the performance is demonstrated by using the synthetic and real images in the case of different specular effects and noisy environments.
ISSN: 1045-9227
DOI: 10.1109/72.883483
Appears in Collections:Journal/Magazine Article

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


Last Week
Last month
Citations as of May 17, 2018

Page view(s)

Last Week
Last month
Citations as of May 21, 2018

Google ScholarTM



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