期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2019
卷号：2241
页码：287-292
出版社：Newswood and International Association of Engineers
摘要：Recently, the demand for ultra-high definition with
4K and 8K panels has increased. The study in this paper
develops a fast algorithm for detecting wiring defects of glass
substrates, which is based on an analysis done on time series
data obtained through non-contact electronic inspection. New
feature quantities with respect to the frequency domain of time
series data are proposed. To demonstrate the effectiveness of
the proposed algorithm, numerical experiments are conducted
using the real sensing data obtained in the field of glass
substrate inspection.
关键词：defect detection; machine learning; glass substrate;
time series data; non;contact inspection; frequencydomain
feature
