Open AccessA method of detecting the feature of cylindrical pin based on machine vision
Author(s) -
YunChuan He,
Gelu Ovidiu Tirian
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1781/1/012033
Subject(s) - chamfer (geometry) , feature (linguistics) , process (computing) , artificial intelligence , computer vision , computer science , filter (signal processing) , pattern recognition (psychology) , mathematics , geometry , philosophy , linguistics , operating system
As a common mechanic part, cylindrical pin is mainly used for positioning the parts in assembling process. Chamfer angle is an important feature of cylindrical pin, which guides the pin into the pin hole. Manual method is used by cylindrical pin manufacturer to detect the chamfer feature and so as to filter the defective products. But it is found that many problems including inevitable subjective error, high intensity of labor, and low detection efficiency exist during manual operation. A new method based on machine vision is proposed in this paper to detect the chamfer feature and size of cylindrical pin. Contour of cylindrical pin is obtained by camera, chamfer feature and size is then extracted through image analysis. Experiment result proves that the method is feasible.