10 February 2006 Shape detection by applying a laser line and neural networks
Author Affiliations +
Proceedings Volume 6046, Fifth Symposium Optics in Industry; 60461L (2006) https://doi.org/10.1117/12.674558
Event: Fifth Symposium Optics in Industry, 2005, Santiago De Queretaro, Mexico
Abstract
A technique for shape detection using a laser line and neural networks is presented. In this technique, an object is scanned by means of a laser line. From the scanning, a set of images is captured by a CCD camera. By processing these images, the object shape is recovered. The topographic information is extracted from an image by detecting the laser line position in the image plane. To determine the mathematical model of the relationship between the laser line position and the object surface, neural networks are applied. To carry it out, Bezier functions are used to construct the architecture of the neural networks. Using neural networks in this technique, the object shape is obtained by image processing and the parameters of the optical set-up are avoided. In this manner, the accuracy of the topographic measurements is improved. The results of this examination are presented by computer simulation and experimentally verified.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
J. Apolinar Muñoz-Rodríguez, J. Apolinar Muñoz-Rodríguez, } "Shape detection by applying a laser line and neural networks", Proc. SPIE 6046, Fifth Symposium Optics in Industry, 60461L (10 February 2006); doi: 10.1117/12.674558; https://doi.org/10.1117/12.674558
PROCEEDINGS
7 PAGES


SHARE
Back to Top