Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.

Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks

Open access
Tao, Xian, Zhang, Dapeng, Ma, Wenzhi, Liu, Xilong, Xu, De · 2018 · Applied Sciences

Abstract

Automatic metallic surface defect inspection has received increased attention in relation to the quality control of industrial products. Metallic defect detection is usually performed against complex industrial scenarios, presenting an interesting but challenging problem. Traditional methods are based on image processing or shallow machine learning techniques, but these can only detect defects under specific detection conditions, such as obvious defect contours with strong contrast and low noise, at certain scales, or under specific illumination conditions. This paper discusses the automatic detection of metallic defects with a twofold procedure that accurately localizes and classifies defects appearing in input images captured from real industrial environments. A novel cascaded autoencoder (CASAE) architecture is designed for segmenting and localizing defects. The cascading network transforms the input defect image into a pixel-wise prediction mask based on semantic segmentation. The defect regions of segmented results are classified into their specific classes via a compact convolutional neural network (CNN). Metallic defects under various conditions can be successfully detected using an industrial dataset. The experimental results demonstrate that this method meets the robustness and accuracy requirements for metallic defect detection. Meanwhile, it can also be extended to other detection applications.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/app8091575

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Challenges of detecting surface defects of metallic components. ( a ) Defects with various shapes and sizes, ( b1 ) defects with ambiguous edges and low contrast, ( b2 ) defects with different background, ( b3 ) fiber, ( b4 ) dust, ( b5 , b6 ) scratches.
Figure 1 Challenges of detecting surface defects of metallic components. ( a ) Defects with various shapes and sizes, ( b1 ) defects with ambiguous edges and low contrast, ( b2 ) defects with different background, ( b3 ) fiber, ( b4 ) dust, ( b5 , b6 ) scratches.CC-BY · From the PDF
Figure 2 The pipeline of the proposed metallic surface defect inspection architecture. ( a ) Original image, ( b ) defect segment, ( c ) defect location, ( d ) cropped results, and ( e ) classification.
Figure 2 The pipeline of the proposed metallic surface defect inspection architecture. ( a ) Original image, ( b ) defect segment, ( c ) defect location, ( d ) cropped results, and ( e ) classification.CC-BY · From the PDF
Figure 3 The architecture of the autoencoder (AE) network.
Figure 3 The architecture of the autoencoder (AE) network.CC-BY · From the PDF
Figure 4 Illustration of atrous convolution.
Figure 4 Illustration of atrous convolution.CC-BY · From the PDF
Figure 5 The architecture of a compact convolutional neural network (CNN).
Figure 5 The architecture of a compact convolutional neural network (CNN).CC-BY · From the PDF
Figure 6 Segmentation results. The six rows are examples of defective images. ( a1 -a6 ) raw images, ( b1 -b6 ) results of Kittler [19], ( c1 -c6 ) results of Otsu [17], ( d1 -d6 ) results of a fully convolutional network (FCN) [36], ( e1 -e6 ) results of the cascaded autoencoder (CASAE) (proposed).
Figure 6 Segmentation results. The six rows are examples of defective images. ( a1 -a6 ) raw images, ( b1 -b6 ) results of Kittler [19], ( c1 -c6 ) results of Otsu [17], ( d1 -d6 ) results of a fully convolutional network (FCN) [36], ( e1 -e6 ) results of the cascaded autoencoder (CASAE) (proposed).CC-BY · From the PDF
Figure 7 Detail classification results of four methods.
Figure 7 Detail classification results of four methods.CC-BY · From the PDF
Figure 8 Examples of CASAE-processed images for different applications. The first columns are examples of ( a1 -a3 ) SEM images, and ( b1 -b3 ) result images of spot defects are marked in green.
Figure 8 Examples of CASAE-processed images for different applications. The first columns are examples of ( a1 -a3 ) SEM images, and ( b1 -b3 ) result images of spot defects are marked in green.CC-BY · From the PDF
Figure 9 Examples of CASAE-processed images with textured backgrounds. The first columns are examples of ( a1 -a3 ) defects images and ( b1 -b3 ) result images of defects marked in green.
Figure 9 Examples of CASAE-processed images with textured backgrounds. The first columns are examples of ( a1 -a3 ) defects images and ( b1 -b3 ) result images of defects marked in green.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 43 references

Research works printed but not linked: 2

  1. Tastimur, 2016, Rail defect detection and classification with real time image processing technique, Int. J. Comput. Sci. Softw. Eng., 5, 283
  2. Kalaiselvi, 2015, A rapid automatic brain tumor detection method for MRI images using modified minimum error thresholding technique, Int. J. Imaging Syst. Technol., 1, 77

Cited by

See all 487

Metadata

Authors
Tao, X., Zhang, D., Ma, W., Liu, X., & Xu, D.
Affiliations
  • Chinese Academy of Sciences (CN)
  • China University of Mining and Technology - Beijing (CN)
Corresponding author
Tao, Xian
Venue
Applied Sciences
Publisher
MDPI AG
Published
2018-09-06
Volume
8
Issue
9
Pages
1575
ISSN
2076-3417 (ISSN-L)
OpenAlex
W2890747436
Cited by
471
References
43
Citations by year
2026: 29 · 2025: 42 · 2024: 60 · 2023: 94 · 2022: 72 · 2021: 82 · 2020: 58 · 2019: 32 · 2018: 2
FWCI
36.08
Type
journal article
Language
en
Open access
Locations
  • Applied Sciences (publishedVersion, cc-by)
  • ELARTU (Ternopil National Technical University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation of China (61703399, 61503376, 61673383)
Topics
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
  • Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
Keywords
defect localization, defect classification, semantic segmentation, convolutional neural networks, manufacturing quality control, industrial inspection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks. https://app.cochat.ai/papers/10.3390/app8091575
The paper
Tao, X., Zhang, D., Ma, W., Liu, X., & Xu, D. (2018). Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks. Applied Sciences. https://doi.org/10.3390/app8091575

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.