Neural-network-based noncontact measurement system

Limin Zhou; Abdul Waheed; Bingheng Lu

doi:10.1117/12.253079

3 October 1996 Neural-network-based noncontact measurement system

Limin Zhou, Abdul Waheed, Bingheng Lu

Proceedings Volume 2899, Automated Optical Inspection for Industry; (1996) https://doi.org/10.1117/12.253079
Event: Photonics China '96, 1996, Beijing, China

Abstract

Now days, the most popular commercial non-contact measurement system uses the triangulation method. To obtain the accurate and quick results of measurement system, the calibration of the system is a must. In this paper, the ANN technology has been used along with laser scanning measurement systems. The image of the given object is measured with the help of a CCD camera and is fed as the input layer to the neural network, whereas the geometrical data of the object surface is the output layer. If the network is properly trained, it will provide the accurate surface fitting. The perceptron model has been adopted and trained by using an improved back-propagation algorithm. The results of the experiments have concluded the higher accuracy of the proposed measurement technique, as well as it is an easy and fast method. It has also eliminated the influence of lens aberration and other factors.

Citation Download Citation

Limin Zhou, Abdul Waheed, and Bingheng Lu "Neural-network-based noncontact measurement system", Proc. SPIE 2899, Automated Optical Inspection for Industry, (3 October 1996); https://doi.org/10.1117/12.253079

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