By Topic

Rapid detection method for fabric defects based on machine vision

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Yao Rong ; State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, China ; Dong He ; Yuchi Lin

A new detection method for the non-destructive test of fabric defects based on machine vision is proposed in this study. In the proposed method, (a) the raw image is pre-processed by figuring the contrast and intensity to a proper level, (b) candidate regions are detected using the HSI color model and dynamic binarization, (c) the characteristic line of the target is obtained by the gray weighted centroid algorithm and (d) the quality of the product is judged by the number of valid pixel in the candidate region and the separation angle calculated from the characteristic line. Taking the detection of diaper as an example, an automatic detection system is built with an industrial camera. The position of diaper elastic waist and angle of the waist label, which are the two major parameters in the test of diaper quality, are examined based on the proposed method. Experimental results indicate that this method can be applied efficiently and effectively while resolving the problem of relative weak illumination and low contrast, bringing down noises caused by wrinkle and stain, and achieving a stable online inspection.

Published in:

2010 International Conference on Computer Application and System Modeling (ICCASM 2010)  (Volume:10 )

Date of Conference:

22-24 Oct. 2010