Founded in 1971 >
Chinese Sci-tech Core Periodicals >
British Science Abstracts (SA, INSPEC) Indexed Journals >
United States, Cambridge Scientific Abstract: Technology (CSA: T) Indexed Journals >
United States, Ulrich's Periodicals Directory(UPD)Indexed Journals >
United States, Cambridge Scientific Abstract: Natural Science (CSA: NS) Indexed Journals >
Poland ,Index of Copernicus(IC) Indexed Journals >
International Standard Serial Number:
ISSN 1001-4551
Sponsor:
Zhejiang University;
Zhejiang Machinery and Electrical Group
Edited by:
Editorial of Journal of Mechanical & Electrical Engineering
Chief Editor:
ZHAO Qun
Vice Chief Editor:
TANG ren-zhong,
LUO Xiang-yang
Tel:
86-571-87041360,87239525
Fax:
86-571-87239571
Add:
No.9 Gaoguannong,Daxue Road,Hangzhou,China
P.C:
310009
E-mail:
meem_contribute@163.com
TANG Xu sheng, YANG Si cai, CHEN Dan
(School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350116, China)
Abstract: Aiming at the problem of automatic detection of the pre weaving cord fabric yarn defect, the analysis of the distribution features of the pre weaving cord fabric yarn defect was conducted and the algorithm for the detection of the cord fabric yarn defect based on the Gabor filters was proposed. The energy value of the Gabor filter was used to describe the defect characteristics of the cord fabric yard. The defect Gabor images were given thresholding process and the binary images of the defect were obtained. Then the defect binary images were equally divided in the horizontal direction to obtain the defect stripe images for removing the random noise. After the accuracy analysis of the defect detection with the Gabor filters with different parameters performed on 1792 test sets of the defect images, the optimal portfolio of the direction and scale of the defect Gabor features was established and the automatic detection system for the cord fabric yarn defect based on the machine vision was constructed. The results indicate that using this method raises the cord fabric yarns defect detection accuracy up to 99.2%. After the actual practices over 4 months, it gives an improvement by 86% compared with the manual detection and achieves the purposes of machine substitutions.
Key words: cord fabric yarn; before weaving; Gabor; defect detection; machine vision