PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Neural adaptive stereo matching
Ignazio Gallo, Elisabetta Binaghi and Mario Raspanti
Neural adaptive stereo matching Volume 25, Number 15, pp. 1743-1758, 2004. ISSN 0167-8655


The present work investigates the potential of neural adaptive learning to solve the correspondence problem within a two-frame adaptive area matching approach. A novel method is proposed based on the use of the Zero Mean Normalized Cross Correlation Coefficient integrated within a neural network model which use least-mean-square delta rule for training. Two experiments were conducted for evaluating the neural model proposed. The first aimed to produce dense disparity maps based on the analysis of standard test images. The second experiment, conducted in biomedical field, aimed to model 3D surfaces from a varied set of SEM (Scanning Electron Microscope) stereoscopic image pairs.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:1871
Deposited By:Ignazio Gallo
Deposited On:29 November 2005