Automatic quality control of seam puckers based on shadow detection
Authors: Ioannis Mariolis, Evangelos Dermatas
Abstract
A novel method performing automatic seam quality control based on visual information is introduced. More specifically, oblique illumination is applied and 2-dimensional grayscale images of seam specimens are acquired. The amount of shadowing present in each image is being estimated through an innovating technique which employs dynamic thresholding and first order statistics. This estimation is used as a measure of seam quality and a simple linear model is constructed for classification by means of ordinary least squares (OLS) regression. The proposed method has been tested in case of 112 seam specimens classified by human experts into five discrete quality grades and a correct classification rate of 84.82% has been produced. Moreover even in case of misclassification the results differ from the correct quality grade only by one unit. The presented results match up to those produced by human observation
| Attachment | Size |
|---|---|
| IPROMS2008.wmv | 8.2 MB |
Welcome to "Intelligent Automation Systems" Session.
I am Ji Young Lee who is a co-chair for this session.
First of all, I thank authors to contribute their papers.
In addition, I welcome all visitors to this session.
In order to post questions and comments or download a paper, you should register at first. It is absolutely free.
I would like to ask Authors to upload their presentation as soon as possible to stimulate the session if it haven't been done yet. If you need any help plese contact me via
email: LeeJ5@cardiff.ac.uk.
Enjoy the session!
Kind regards,
Ji Young Lee
Intelligent Automation Systems Session Co-Chair
IPROMS 2008