The DOI matches its Crossref record; 88 of the 93 references it cites were found in a registry or an index; 14 of the 179 sources its claims cite were checked for support.
Review of vision-based steel surface inspection systems
Open accessAbstract
Steel is the material of choice for a large number and very diverse industrial applications. Surface qualities along with other properties are the most important quality parameters, particularly for flat-rolled steel products. Traditional manual surface inspection procedures are awfully inadequate to ensure guaranteed quality-free surface. To ensure stringent requirements of customers, automated vision-based steel surface inspection techniques have been found to be very effective and popular during the last two decades. Considering its importance, this paper attempts to make the first formal review of state-of-art of vision-based defect detection and classification of steel surfaces as they are produced from steel mills. It is observed that majority of research work has been undertaken for cold steel strip surfaces which is most sensitive to customers' requirements. Work on surface defect detection of hot strips and bars/rods has also shown signs of increase during the last 10 years. The review covers overall aspects of automatic steel surface defect detection and classification systems using vision-based techniques. Attentions have also been drawn to reported success rates along with issues related to real-time operational aspects.
Overview
CoChat Summary
## TL;DR
This paper is a review of vision-based automated steel surface inspection systems, covering defect detection/classification methods, hardware, and commercial developments across roughly two and a half decades of literature. It concludes that automated inspection has matured but remains challenging because of harsh mill conditions, noisy images, high line speeds, and the lack of common standards for defects and benchmarking.
## Key findings
- The authors state this is the “first formal review” of state-of-the-art vision-based defect detection and classification of steel surfaces, consolidating literature from academia, steel industry, and manufacturers.
- Research focus has been uneven: the abstract says “majority of research work” has been on cold steel strip surfaces, while hot strips and bars/rods have gained more attention in the last 10 years.
- The review reports very high variation in operating speed: steel objects ranged from 2 to 100 m/s, with about 20 m/s typical for hot strip and cold strip, and up to 100 m/s for wire rods.
- Reported classification/detection performance examples include 98% accuracy for multifractal-based classification of five cold-strip defect types, 99% accuracy for adaptive wavelet packet + NN-BP on eight cold-strip defect types, and 94% overall result for a weak-classifier cascade on six cold-strip defect types.
- The paper notes that commercial systems are commercially available from the 1970s, became common in steel inspection since the 1990s, and today are produced by manufacturers such as ISRA-Parsytec, ABB, Siemens, and Cognex.
## Methods
- Narrative literature review of published work over approximately two and a half decades on automatic vision-based steel surface defect detection and classification.
- The review organizes the literature by steel product type, defect types, hardware elements (light source, camera, processor, server, operator interface), and algorithm families.
- It compares representative detection/classification systems using reported sample sizes, image resolutions, speeds, and accuracies from prior papers and tables in the review.
## Limitations
- The paper explicitly states that it is not prudent to compare outcomes of different techniques because there is no common standard for images, experimental methods, or even defect definitions.
- It also states that details of defect detection and classification techniques in commercial systems are often not elaborated, “probably due to issues regarding intellectual property rights.”
- Evident from the text: this is a review, not a new experimental study, so its conclusions depend on the quality and comparability of the cited literature.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
13 Valid · 35 Not valid · 93 Not checked · 98 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“In a large number of instances [3,35,41,42,56,58,61], it has been possible to localise RoIs with a high degree of accuracy.”
What the sources say
- Not matchedcites [3] Sharifzadeh M, Alirezaee S, Amirfattahi R, Sadri S: Detection of Steel Defect Using the Image Processing Algorithms. IEEE International Multitopic Conference; 2008:125-127.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [35] Weiwei L, Yunhui Y, Jun L, Yao Z, Hongwei S: Automated On-Line Fast Detection for Surface Defect of Steel Strip Based on Multivariate Discriminant Function. IEEE Second International Symposium on Intelligent Information Technology Application; 2008:493-497. source
- Not matchedcites [41] Xiu-yong W, Ke X, Jin-wu X: Application of Undecimated Wavelet Transform to Surface Defect Detection of Hot Rolled Steel Plates. IEEE Congress on Image and, Signal Processing; 2008:528-532.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [42] Cord A, Bach F, Jeulin D: Texture classification by statistical learning from morphological image processing: application to metallic surfaces. J. Microsc. 2010, 239(2):159-166. source
The Results on metallic surfaces at the image level report that defects were well located across 800 images, with 98.5% accuracy. This supports the cited paper as an example of accurate localisation of regions of interest, although its specific regions were surface defects. (LLM, conf=0.91)
- Not checked — no full text of the sourcecites [56] Cong JH, Yan YH, Zhang HA, Li J: Real-time surface defects inspection of steel strip based on difference image, international symposium on photoelectronic detection and imaging, related technologies and applications. Proc of SPIE 2007, 6625: 1-9. source
- Not matchedcites [58] Li W, Lu C, Zhang J: A local annular contrast based real time inspection algorithm for steel bar surface defects. Appl. Surf. Sci. 2010. doi:10.1016/j.apsusc.2012.03.007
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [61] Choi SH, Yun JP, Seo B, Park Y, Kim SW: Real-time defects detection algorithm for high-speed steel bar in coil, world academy of science. Eng Technol 2007, 25: 66-70.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“First-order gradient filter followed by thresholding is more commonly used for edge localisation [2,44,46,59,76] due to its noise immunity characteristics compared to Laplacian.”
What the sources say
- Not checked — no full text of the sourcecites [2] Jia H, Murphey YL, Shi J, Chang T: An Intelligent Real-time Vision System for Surface Defect Detection. IEEE-Proceedings of the 17th International Conference on Pattern Recognition; 2004:2-5. source
- Not checked — no full text of the sourcecites [44] Yun JP, Park C, Bae H, Hwang H, Choi S International Conference on Control, Automation and Systems 2010, vol. 1. In Vertical Scratch Detection Algorithm for High-speed Scale-covered Steel BIC (Bar in Coil). KINTEX, Gyeonggi-do, Korea; 2010:342-345. source
- Not checked — no full text of the sourcecites [46] Suresh BR, Fundakowski RA, Levitt TS, Overland JE: A real-time automated visual inspection system for hot steel slabs. IEEE Trans. Pattern Anal. Mach. Intell. 1983, PAMI-5(6):563-572. source
- Not checked — no full text of the sourcecites [59] Liu Y, Hsu Y, Sun Y, Tsai S, Ho C, Chen C: A Computer Vision System for Automatic Steel Surface Inspection. The fifth IEEE conference on Industrial Electronics and Applications (ICIEA); 2010:1667-1670. source
- Partly supportedcites [76] Blackledge JM, Dubovitskiy DA: A surface inspection machine vision system that includes fractal texture analysis, international society for advanced science and technology. J Intell Syst 2008, 3(2):76-89. sourceExperimental — accuracy not yet measured
In “Background to the Case” (page unavailable), the paper uses a Sobel edge detector to provide a rough location for defects, supporting the edge-localisation portion of the claim. Our copy does not say that gradient filtering is followed by thresholding, is more commonly used, or has better noise immunity than a Laplacian filter; searches for those terms found no such comparison. (LLM, conf=0.78)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“SVM was used with 12 geometric and gray-level features in [65] and seven histogram and gradient-based features in [67] as inputs to detect one type of defect in plate and slab with 85% and 94% accuracy, respectively.”
What the sources say
- Partly supportedcites [65] Choi DC, Jeon YJ, Yun JP, Yun SW, Kim SW: An algorithm for detecting seam cracks in steel plates. World Acad Sci Eng Technol 2012, 6: 1456-1459. sourceExperimental — accuracy not yet measured
The Introduction (p. 2835) identifies seam cracks in steel plates as the detection target, and the Feature Extraction section (p. 2836) lists shape-related features and gray-value difference. The passages available from our copy do not establish that the method used SVM, had 12 input features, or achieved 85% accuracy. (LLM, conf=0.78)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Thus, it has been widely used for separation of defects from pseudo defects in steel surfaces [2,5,44,47,65,67].”
What the sources say
- Not checked — no full text of the sourcecites [2] Jia H, Murphey YL, Shi J, Chang T: An Intelligent Real-time Vision System for Surface Defect Detection. IEEE-Proceedings of the 17th International Conference on Pattern Recognition; 2004:2-5. source
- Not checked — no full text of the sourcecites [5] Park C, Won SC: An automated web surface for hot wire rod using undecimated wavelet transform and support vector machine. Industrial Electronics, IECON'09, 35th Annual Conference of IEEE; 2009:2411-2415. source
- Not checked — no full text of the sourcecites [44] Yun JP, Park C, Bae H, Hwang H, Choi S International Conference on Control, Automation and Systems 2010, vol. 1. In Vertical Scratch Detection Algorithm for High-speed Scale-covered Steel BIC (Bar in Coil). KINTEX, Gyeonggi-do, Korea; 2010:342-345. source
- Not matchedcites [47] Choi DC, Jeon YJ, Lee SJ, Yun JP, Kim SW: Oilmarks Detection Algorithm in Steel Plates, Latest Trends on Systems. I: 239-242. ISBN 978-1-61804-243-9
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Partly supportedcites [65] Choi DC, Jeon YJ, Yun JP, Yun SW, Kim SW: An algorithm for detecting seam cracks in steel plates. World Acad Sci Eng Technol 2012, 6: 1456-1459. sourceExperimental — accuracy not yet measured
The Method section describes using extracted features to distinguish seam cracks from pseudo defects in steel plates. It does not identify SVM as the method or establish that SVM is widely used for this purpose (searched: SVM, support vector machine, classifier). (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [67] Jeon Y, Choi D, Yun J, Park C, Kim SW: Detection of Scratch Defects on Slab Surface, 1th International Conference on Control, Automation and Systems. 2011, 1274-1278.
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These defects are not governed by any standard.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
56 more claims
Create a free account to see all 239 claims and every source verdict.
- Probably not a substantial claim. 161
- It may state two separate claims as one. 48
- The quote only partly states this claim. 2
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?
The cited source says what the claim attributes to it.
In the citing paper
“In terms of shape, the steel surface can be divided into flat products and long products [11].”
From Steel Surface Defect Recognition: A Survey (2022) · cites this paper as [11]
In the citing paper
“The process of detecting and classifying defects of the surface of metal strips usually occurs in three stages [9]:”
From Real-time system for automatic cold strip surface defect detection (2019) · cites this paper as [9]
In the citing paper
“However, these surveys paid more attention to the detection methods, and they simply summarized the research progress of the classification methods through supervised and unsupervised classifiers.”
From Automated Visual Defect Classification for Flat Steel Surface: A Survey (2020) · cites this paper as [29]
Citations
Cites
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Neural networks: A comprehensive foundation
Tadeusiewicz, R. (1995) · Control Engineering Practice · doi:10.1016/0967-0661(95)90080-2 · Cited by 7,218
Gomarasca, M. A. (2009) · Basics of Geomatics · doi:10.1007/978-1-4020-9014-1_8 · Cited by 2,614
Computer-Vision-Based Fabric Defect Detection: A Survey
Kumar, A. (2008) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.1930.896476 · Cited by 725
A Survey of Automated Visual Inspection
Newman, T. S., & Jain, A. K. (1995) · Computer Vision and Image Understanding · doi:10.1006/cviu.1995.1017 · Cited by 619 · cited 1×
“Over the years, a number of review papers [6-12] on various aspects of surface defect detection have been reported.”
Background(1998) · Cited by 540
A Review of Recent Advances in Surface Defect Detection using Texture analysis Techniques
Xie, X. (2008) · ELCVIA Electronic Letters on Computer Vision and Image Analysis · doi:10.5565/rev/elcvia.268 · Cited by 500 · cited 3×
“Over the years, a number of review papers [6-12] on various aspects of surface defect detection have been reported.”
BackgroundMethodAutomated Visual Inspection: A Survey
Chin, R. T., & Harlow, C. A. (1982) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1982.4767309 · Cited by 400
IEEE 2005 International Conference on Image Processing
(2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2004.833947 · Cited by 386
Free-form surface inspection techniques state of the art review
Li, Y., & Gu, P. (2004) · Computer-Aided Design · doi:10.1016/j.cad.2004.02.009 · Cited by 371
Research works printed but not linked: 16
- Guha P M. Tech dissertation. In Automated Visual Inspection of Steel Surface, Texture Segmentation and Development of a Perceptual Similarity Measure. IIT, Kanpur; 2001.
- Muehlemann M: Standardizing Defect Detection for the Surface Inspection of Large Web Steel. Illumination Technologies Inc; 2000. URL: , 2000, pp. 1–9, access July '12 http://www.illuminationtech.com/documents/surface_inspection.pdf URL: , 2000, pp. 1–9, access July '12
- Toshihiro S, Hideki T, Yasuo T: Automatic Surface Inspection System for Tin Mill Black Plate (TMBP). JFE TECHNICAL REPORT 2007, 9: 60-63.
- Järvinen J, Rauhamaa J: Real-time inspection of steel strip, European stainless steel conference. 2003. URL: $file/. accessed July '12 http://www05.abb.com/global/scot/scot227.nsf/veritydisplay/40b5916e13f4c0b5c125764a003a3352/ URL: $file/. accessed July '12
- Gangadaran M, Mitra S, Kumar D, Kumar R, Saha SK, Gupta P, Prasad BK, Singh AKP, Gangadaran M, Mitra S, Kumar D, Kumar R, Saha SK, Gupta P, Prasad BK, Singh AKP: Online Surface Inspection System for Hot Rolled flat surface, a journey of development, ISIS INDIA. International Surface Inspection Summit, ISIS INDIA; 2012.
- Simonis MP: Strip Surface Inspection, MILLENNIUM STEEL. 2006, 218-222. URL: , accessed July '12 http://www.millennium-steel.com/articles/pdf/2006/pp218-222%20MS06.pdf URL: , accessed July '12
- Yun JP, Park C, Yun SW, Bae H, Choi S: Surface Defect Inspection System for hot Scarfed Slab ISIS INDIA 2012. International Surface Inspection Summit; 2012.
- Maenpaa T: Surface Quality Assessment with Advanced Texture Analysis Techniques. Proc. of International Surface Inspection Summit, Luxembourg; 2006.
- Ünsalan C, Erçil A: Automated Inspection of Steel Structures, Recent Advances in Mechatronics. Springer-Verlag Ltd., Singapore; 1999:468-480.
- Choi SH, Yun JP, Seo B, Park Y, Kim SW: Real-time defects detection algorithm for high-speed steel bar in coil, world academy of science. Eng Technol 2007, 25: 66-70.
- Jonker PP, Duin RPW, Ridder DD: Pattern recognition for metal defect detection. Steel Grips 2003, 1(1):20-23.
- Ayani A, Lago A, Cruz A: Surface Inspection of hot Rolled Seamless Tube, Journals-Chernye Metally (Ferrous Metals). 2009. #4
- Jin N, Zhou S, Chang T: Identification of Impacting Factors of Surface Defects in hot Rolling Processes Using Multi-Level Regression Analysis. Transactions of NAMRI/SME 2004, 32: 557-564.
- Huang H, Gutchess D, Chang T: Imaging-based In-Line Surface Defect Inspection for Bar Rolling, AIST Iron & Steel Conference and Exposition. AIST Digital Library, Nashville, TN; 2004.
- Tivolle A, Legrand J, Keods: Fully Integrated Management of Automatic Surface Inspection Systems. India; 2012. ISIS
- Chang TS, Gutchess D, Huang HH Annual Portfolio Review. The Advancement in Surface Quality Assurance for hot Rolled Steel Bars, DOE Sensors & Automation 2005, 1-19.
Cited by
Deep learning for smart manufacturing: Methods and applications
Wang, J., Ma, Y., Zhang, L., Gao, R. X., & Wu, D. (2018) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2018.01.003 · Cited by 1,740
Chen, F.-C., & Jahanshahi, M. R. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2764844 · Cited by 930
“Recent vision-based steel surface inspection systems have been reviewed in [3] including crack detection algorithms.”
BackgroundMethodWeimer, D., Scholz-Reiter, B., & Shpitalni, M. (2016) · CIRP Annals · doi:10.1016/j.cirp.2016.04.072 · Cited by 577
“[2], existing methods roughly be divided into four main categories: statistical, structu filter based, and model based.”
MethodAutomated Visual Defect Detection for Flat Steel Surface: A Survey
Luo, Q., Fang, X., Liu, L., Yang, C., & Sun, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2963555 · Cited by 559
“Notably, a brief but rare AVI review covering defect detection and classification techniques for steel products was reported [9], where nearly all types of steel products (slab, billet, plate, hot strip, cold strip, rod/bar) are involved at an overview level.”
BackgroundKhalil, R. A., Saeed, N., Masood, M., Fard, Y. M., Alouini, M.-S., & Al-Naffouri, T. Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3051414 · Cited by 318
Metadata
- Authors
- Neogi, N., Mohanta, D. K., & Dutta, P. K.
- Affiliations
- Birla Institute of Technology, Mesra (IN)
- Indian Institute of Technology Kharagpur (IN)
- Venue
- EURASIP Journal on Image and Video Processing
- Published
- 2014-11-13
- Volume
- 2014
- Issue
- 1
- ISSN
- 1687-5176 (ISSN-L)
- 1687-5281
- OpenAlex
- W2155903085
- Cited by
- 322
- References
- 93
- Citations by year
- 2026: 28 · 2025: 29 · 2024: 32 · 2023: 37 · 2022: 30 · 2021: 37 · 2020: 26 · 2019: 28 · 2018: 32 · 2017: 20 · 2016: 18 · 2015: 5
- FWCI
- 26.96
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- EURASIP Journal on Image and Video Processing (publishedVersion, cc-by)
- 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 classification, flat-rolled steel, hot-rolled strip, automated inspection system, real-time 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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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: Review of vision-based steel surface inspection systems. https://app.cochat.ai/papers/10.1186/1687-5281-2014-50
- The paper
- Neogi, N., Mohanta, D. K., & Dutta, P. K. (2014). Review of vision-based steel surface inspection systems. EURASIP Journal on Image and Video Processing. https://doi.org/10.1186/1687-5281-2014-50
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.