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: In the visual detection of contact spots on worm gear pairs, the overall brightness and contrast of the images collected by the camera are low, resulting in unsatisfactory image detection results,so it is necessary to use image enhancement technology to enhance the brightness, contrast, and other information of the image. Therefore, an image quality enhancement algorithm based on channel stretching and improved multi-scale Retinex (MSR) was proposed. Firstly, in low light environment, channel stretching was carried out to enhance the image saturation and contrast, to avoid color distortion in the process of image detail enhancement. Then, in order to further increase the contrast of the image details, the improved MSR algorithm was used to process the stretched image. The Gaussian center surround function and logarithm function in the traditional MSR were replaced by adaptive weight bilateral filtering and tanh function to reduce the loss of detail information. Finally, adaptive gamma transform was used to further improve the image brightness, so that the quality of the image was higher and the image was convenient for subsequent processing. The experimental results show that comparing with MSR and the improved MSR enhancement algorithm based on bilateral filtering, the enhancement effect of the image enhancement algorithm for contact spots of worm gear pairs based on channel stretching and improved multiscale Retinex is better. Comparing with the original image, the mean value, standard deviation, information entropy and contrast of the image after the enhancement are respectively increased by 48.3%, 61.6%, 7.1% and 91.3%. The results show that the enhanced image quality and feature information are better after adopting this image enhancement algorithm,which is conducive to image detection and processing.
Key words: worm gear and worm accuracy; visual detection of contact spots of worm gear pair; image enhancement technology; multi-scale Retinex (MSR); color space; adaptive weighted bilateral filtering; adaptive gamma transform