2018
DOI: 10.1109/access.2018.2852663
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Visual Defect Detection Using Texture Prior and Low-Rank Representation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
30
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 44 publications
(30 citation statements)
references
References 18 publications
0
30
0
Order By: Relevance
“…Susan et al [96] proposed Gaussian mixture entropy model for defect detection, which is specialized in identifying miscellaneous defects such as holes and stains. Based on low-rank representation, Yan et al [97] utilized smooth-sparse decomposition (SSD) model for anomaly detection in images, Huangpeng et al [98] proposed a novel weighted low-rank reconstruction model for automatic visual defect detection, and Zhou et al [99] presented a double low-rank and sparse decomposition (DLRSD) model to obtain the defective region of steel sheet surface. These approaches are reported to perform well.…”
Section: ) Other Latest Reported Model-basedmentioning
confidence: 99%
“…Susan et al [96] proposed Gaussian mixture entropy model for defect detection, which is specialized in identifying miscellaneous defects such as holes and stains. Based on low-rank representation, Yan et al [97] utilized smooth-sparse decomposition (SSD) model for anomaly detection in images, Huangpeng et al [98] proposed a novel weighted low-rank reconstruction model for automatic visual defect detection, and Zhou et al [99] presented a double low-rank and sparse decomposition (DLRSD) model to obtain the defective region of steel sheet surface. These approaches are reported to perform well.…”
Section: ) Other Latest Reported Model-basedmentioning
confidence: 99%
“…However, if the defected region is relatively large, this may be reflected to the background features and will affect the background reconstruction method [351]. Furthermore, this method can only solve LCD images with simple background [352]. Similar to PCA, Singular Value Decomposition (SVD) is another linear method used to extract the significant feature components of the image, which can be also used to calculate PCs.…”
Section: ) Model-based Feature Extractionmentioning
confidence: 99%
“…Recently, although deep learning-based approaches have been used to solve several problems in the field of civil engineering, some problems are complex, and more optimal approaches than deep learning-based approaches have sometimes been used (Amezquita-Sanchez & Adeli, 2015b;Huangpeng, Zhang, Zeng, & Huang, 2018;Liao, 2017;Poskus, Rodgers, Zhou, & Chase, 2018;Qarib and Adeli, 2015;Wang, Zhang, Wang, Braham, & Qiu, 2018). For example, Wang et al (2018) developed an automatic method for measuring crack width using binary crack map images.…”
Section: Related Work Smentioning
confidence: 99%
“…They introduced a new crack width definition and formulated it using the Laplace equation so that crack width can be continuously and unambiguously measured, and they showed that their method was effective for characterizing propagation behavior of cracks with small widths. Although cracks are one of the most important types of distress, methods for detecting other types of distress have also been studied (Huangpeng et al., ; Poskus et al., ). Huangpeng et al focused on the use of texture features to construct prior maps for distress detection.…”
Section: Related Workmentioning
confidence: 99%