期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：252
期号：2
页码：1-9
DOI：10.1088/1755-1315/252/2/022076
出版社：IOP Publishing
摘要：A defect detection method based on template matching is proposed in the environment of detection of stamping parts in industrial manufacturing. Contours of the part can be obtained by the edge detection algorithm, therefore, we can calculate the deviation matrix of the input image and the standard image by establishing the template feature library of these contours. Then, Compare the deviation matrix and the feature of the contour in the defect position which is confirmed by using two threshold filters to realize the automatic detection of the surface defect of the part. In addition, algorithms include filtering noise reduction and curve fitting are used to improve the overall quality of this detection method. Experiment results show that the surface defect detection method based on template matching has advantages of high adaptability and low time complexity. The accuracy rate of the optimized algorithm can reach over 95% in case that the number of templates is sufficient. The algorithm is suitable for real-time detection of industrial assembly line manufacture.
