Open AccessReal‐time comprehensive glass container inspection system based on deep learning framework
Author(s) -
Liang Qiaokang,
Xiang Shao,
Long Jianyong,
Sun Wei,
Wang Yaonan,
Zhang Dan
Publication year - 2019
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2018.6934
Subject(s) - container (type theory) , computer science , deep learning , quality (philosophy) , artificial intelligence , control (management) , manufacturing engineering , systems engineering , industrial engineering , machine learning , engineering , mechanical engineering , philosophy , epistemology
Reusable glass containers have become extremely popular in recent years due to their cost effectiveness. Quality control such as inspecting and identifying container defects is an essential part of the reusable containers production systems. Many aspects of modern society already benefit from developments in machine learning (ML) technology. However, to the authors’ knowledge, the ML technology approaches have not been extensively applied in the practical inspection instrumentations for glass containers. In this Letter, a comprehensive inspection system for reusable containers based on a deep learning framework is proposed. The experimental results demonstrated that the developed system is capable of inspecting defects of glass containers with superior accuracy and speed. After the success of other practical applications with deep learning approaches, they wish that this Letter could inspire more and more research results in deep learning methods to be widely applied to comprehensive inspection tasks.