Share Email Print

Proceedings Paper

3D shape detection based on a Bezier neural network of a light line
Author(s): J. Apolinar Munoz Rodriguez; Miguel Rosales Cisena; Ramon Rodriguez-Vera
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A simple technique for object shape detection is presented. In this technique, the object is moved along of an axis and scanned by a light line. The object shape is reconstructed by processing a set of images of a light line, which are captured in the scanned step. The profile of the object is obtained applying a Bezier Neural Network. This network is built using data from images of a light line projected onto the known objects. The data from the images are extracted by applying Gaussian approximation. This approximation corresponds to the model of a light line, whose intensity distribution is Gaussian. By using the neural networks in this technique, the object shape is determined without the geometry parameters of the set-up. In this way, the accuracy is improved, because the errors of the set-up parameters are not introduced in the system. To determine the accuracy, a root mean square is calculated using as reference a contact method. This technique is tested with simulation and its experimental results are presented.

Paper Details

Date Published: 14 February 2005
PDF: 10 pages
Proc. SPIE 5776, Eighth International Symposium on Laser Metrology, (14 February 2005);
Show Author Affiliations
J. Apolinar Munoz Rodriguez, Ctr. de Investigaciones en Óptica, A.C. (Mexico)
Miguel Rosales Cisena, Ctr. de Ingenieria y Desarollo Industrial (Mexico)
Ramon Rodriguez-Vera, Ctr. de Investigaciones en Óptica, A.C. (Mexico)

Published in SPIE Proceedings Vol. 5776:
Eighth International Symposium on Laser Metrology
R. Rodriguez-Vera; F. Mendoza-Santoyo, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?