3D shape detection based on a Bezier neural network of a light line

J. Apolinar Munoz Rodriguez; Miguel Rosales Cisena; Ramon Rodriguez-Vera

doi:10.1117/12.611840

14 February 2005 3D shape detection based on a Bezier neural network of a light line

J. Apolinar Munoz Rodriguez, Miguel Rosales Cisena, Ramon Rodriguez-Vera

Proceedings Volume 5776, Eighth International Symposium on Laser Metrology; (2005) https://doi.org/10.1117/12.611840
Event: Eighth International Conference on Laser Metrology, 2005, Merida, Mexico

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.

Citation Download Citation

J. Apolinar Munoz Rodriguez, Miguel Rosales Cisena, and Ramon Rodriguez-Vera "3D shape detection based on a Bezier neural network of a light line", Proc. SPIE 5776, Eighth International Symposium on Laser Metrology, (14 February 2005); https://doi.org/10.1117/12.611840

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available