2019
DOI: 10.1364/oe.27.020910
|View full text |Cite
|
Sign up to set email alerts
|

Automatic scratch detector for optical surface

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2020
2020
2025
2025

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 16 publications
(3 citation statements)
references
References 17 publications
0
3
0
Order By: Relevance
“…Cap defect detection results: Existing image segmentation methods are mainly divided into the following categories: threshold-based, edge-based [ 24 , 25 ] and methods based on specific theories. Since the captured image usually contains spot-like Gaussian noises and may have uneven surfaces and inhomogeneous illuminations, the contrast between the defects and the background information is usually not that high.…”
Section: Methodsmentioning
confidence: 99%
“…Cap defect detection results: Existing image segmentation methods are mainly divided into the following categories: threshold-based, edge-based [ 24 , 25 ] and methods based on specific theories. Since the captured image usually contains spot-like Gaussian noises and may have uneven surfaces and inhomogeneous illuminations, the contrast between the defects and the background information is usually not that high.…”
Section: Methodsmentioning
confidence: 99%
“…At present, plenty of qualitative defect detection methods have been developed, among which the human visual inspection method [1] is widely applied. However, this method has low efficiency and accuracy because it depends greatly on the operator's experience [2]. To solve these problems, the machine vision technique is developed using different image processing algorithms.…”
Section: Introductionmentioning
confidence: 99%
“…One showed an inventory of an optical pickup unit for light reflection into the charge coupled device (CCD) with polarizers and Infrared-(IR) cut filters for intensification of the laser beam [6]. However, for better resolution, machine vision inspection methods using various algorithms to examine the 2D surface images have also been studied but they can only be measured in static state [7]. In addition, it is still a vast cost of investment for industry.…”
Section: Introductionmentioning
confidence: 99%