Open AccessFeatures of translucent materials and products defects detection with support of optical system
Author(s) -
В. В. Булатов,
A. A. Kul’chitskii
Publication year - 2020
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 - 10.1088/1742-6596/1515/5/052007
Subject(s) - brightness , feature (linguistics) , computer science , artificial intelligence , computer vision , pattern recognition (psychology) , optics , physics , philosophy , linguistics
The translucent materials and products defects detection by optical methods are published in the article. The methods are described on quality assessment of sheet glass. There is an application approach based on complex feature. The recognition algorithm is based on three main feature types of defect: brightness, color (primary features) and geometrical or features of shape (secondary). In the document main (algorithmic) and technical sides of creation of machine vision system are described.