A Neural-Learning-Based Reflectance Model for 3-D Shape Reconstruction

Siu Yeung Cho, Tommy W.S. Chow

Research output: Journal PublicationArticlepeer-review

31 Citations (Scopus)

Abstract

In this letter, the limitation of the conventional Lambertian reflectance model is addressed and a new neural-based reflectance model is proposed of which the physical parameters of the reflectivity under different lighting conditions are interpreted by the neural network behavior of the nonlinear input-output mapping. The idea of this method is to optimize a proper reflectance model by a neural learning algorithm and to recover the object surface by a simple shape-from-shading (SFS) variational method with this neural-based model. A unified computational scheme is proposed to yield the best SFS solution. This SFS technique has become more robust for most objects, even when the lighting conditions are uncertain.

Original languageEnglish
Pages (from-to)1346-1350
Number of pages5
JournalIEEE Transactions on Industrial Electronics
Volume47
Issue number6
DOIs
Publication statusPublished - 2000
Externally publishedYes

Keywords

  • Heuristic global learning algorithm
  • Neural network
  • Shape from shading
  • Three-dimensional reconstruction

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Neural-Learning-Based Reflectance Model for 3-D Shape Reconstruction'. Together they form a unique fingerprint.

Cite this