![](http://www.meem.com.cn/static/fore_en/images/logo_01.jpg)
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
Abstract: Aiming at the problems of low efficiency and high influence of human factors in manual inspection of gear defects, a detection method of water meter gear-defect based on machine vision technology was proposed. Firstly, the overall scheme of the water meter gear visual inspection system was designed, and a three-dimensional model of gear visual inspection system was constructed. Secondly, the median filtering method was used for image smoothing processing of the collected images and the edge extraction was done by using the Canny operator. Then, the template matching algorithm combined image pyramid and shape matching was used to find the position relationship between the gear edge contour and the template, and both of their center of gravity could be overlapped by using affine transformation operator. Finally, the maximum error between the template and the outer profile of the gear to be detected was extracted by calculating the Hausdorff distance between the two to identify defective products. A testing platform was established to test the actual gears and verify the gear defect detection system. The experimental results show that the proposed method can effectively detect the defects in the bearing end face. The false detection rate is less than 2% and the undetected rate is less than 1%. The detection time is less than 40ms. The proposed algorithm can meet the requirements of on-line inspection.
Key words: gear transmission; median filtering technology; Canny operator; gear edge contour extraction; gear defect on-line inspection; template matching algorithm; Hausdorff distance; image smoothing processing
![](http://www.meem.com.cn/static/fore_en/images/foot_01.png)