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：3
页码：1-11
DOI：10.1088/1755-1315/252/3/032104
出版社：IOP Publishing
摘要：In this paper, a fast and accurate image segmentation algorithm is studied in this paper, which is based on the automatic optic inspection (AOI) equipment device of the experimental prototype surface array camera printed circuit board (PCB), which is built in the laboratory. In the search for "ridge lines" in the "topography" watershed, three thinning algorithms, skeleton algorithm, watershed algorithm and so on are used for image morphological processing. The experimental comparison shows that the improved watershed algorithm, which combines the related morphological processing, has a remarkable effect on image segmentation, and it can lay a good foundation for the detection and detection of the following PCB board defect recognition.
